© 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. 71768
    Prev
    Next
    INDEX
    Explanations

    provided that

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

    technical computing and AI concepts

    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
     រ
    0.41
    Capability
    0.41
    ints
    0.39
    inado
    0.39
    ]}$.
    0.39
     జగ
    0.38
     reflexive
    0.38
    Coef
    0.38
     paradox
    0.38
    inito
    0.37
    POSITIVE LOGITS
     dwa
    0.53
    骅
    0.50
    素敵
    0.50
    不错
    0.49
    设有
    0.46
    s
    0.46
    десят
    0.46
    łe
    0.45
     dwóch
    0.45
    드가
    0.45
    Activations Density 0.000%

    No Known Activations