© 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. 222683
    Prev
    Next
    INDEX
    Explanations

    nm TX

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

    risks and safety regulations

    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
     disintegrated
    0.44
    ಳ್ಳ
    0.43
     sweetened
    0.43
    <unused56>
    0.42
    SINGLE
    0.42
    ፕሮ
    0.42
     oiled
    0.42
     undetectable
    0.42
    ACTIVE
    0.41
    옳
    0.41
    POSITIVE LOGITS
     осень
    0.52
     OpenCV
    0.48
    kens
    0.47
     regenv
    0.45
     OFDM
    0.44
    .
    0.43
     RoHS
    0.43
     тему
    0.42
    welt
    0.41
     устойчи
    0.41
    Activations Density 0.000%

    No Known Activations