© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 58016
    Prev
    Next
    INDEX
    Explanations

    never sleeps, had not grasped proper, said it has been, want you to be

    np_acts-logits-general · gemini-2.5-flash-lite

    determining sex, heterogeneity, manage light, intentTalk or intentMusic, inventory, adapted, prompt, reply back, connecting people, log

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    兖
    0.55
    reflectionMap
    0.54
     چیر
    0.53
     Chicago
    0.52
     arugula
    0.51
    മല്ല
    0.51
     OKC
    0.51
    言う
    0.50
     Exile
    0.50
    槟
    0.50
    POSITIVE LOGITS
     empec
    0.50
     determinations
    0.46
     spezial
    0.45
    agées
    0.45
    x
    0.45
    -'
    0.44
     personalized
    0.42
     sued
    0.42
    ínguez
    0.42
    diendo
    0.41
    Activations Density 0.000%

    No Known Activations