© 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. 209472
    Prev
    Next
    INDEX
    Explanations

    online search, by undermining, during this

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

    $ and statistical descriptions

    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
    ㅣ
    0.44
     malice
    0.43
    će
    0.42
    Carte
    0.42
    सीएम
    0.42
    De
    0.42
    Cart
    0.42
     surprise
    0.42
    분이
    0.41
    Ink
    0.41
    POSITIVE LOGITS
    $
    0.48
     Hilbert
    0.45
     HT
    0.44
    ${\
    0.43
     muu
    0.41
     фер
    0.41
     HV
    0.40
     Fitbit
    0.40
    🐡
    0.40
     Registrar
    0.39
    Activations Density 0.001%

    No Known Activations