© 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. 134017
    Prev
    Next
    INDEX
    Explanations

    unauthorized substances or actions

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

    minor repairs, purpose, formula, lid

    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
    விரி
    0.53
    Collected
    0.50
     gathered
    0.50
     собира
    0.50
    GRADE
    0.49
     hermanos
    0.49
    IGR
    0.49
    𒃻
    0.48
    ضی
    0.48
     Collected
    0.48
    POSITIVE LOGITS
    曾
    0.51
     لإ
    0.47
     jar
    0.45
    كَ
    0.45
    先
    0.44
     leak
    0.43
    閃
    0.42
     be
    0.42
    ك
    0.42
    se
    0.41
    Activations Density 0.001%

    No Known Activations