© 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. 148961
    Prev
    Next
    INDEX
    Explanations

    or, in, into, even

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

    planning, archive, project, event

    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
    鍾
    0.52
     هيكون
    0.46
    輕
    0.46
    甠
    0.46
    مح
    0.45
    飯店
    0.45
    莗
    0.44
    仯
    0.42
    эро
    0.41
    Ջ
    0.41
    POSITIVE LOGITS
     commutative
    0.46
     electrons
    0.45
     publicity
    0.44
    electrons
    0.44
     itinerant
    0.43
     affixed
    0.43
     electronics
    0.43
     thrust
    0.42
     lubric
    0.42
     commotion
    0.42
    Activations Density 0.000%

    No Known Activations