© 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. 3633
    Prev
    Next
    INDEX
    Explanations

    classic question

    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
     makin
    0.55
     меня
    0.50
     posible
    0.48
     outsider
    0.47
    más
    0.46
     lakini
    0.46
     briefing
    0.46
    🥳
    0.46
    jail
    0.45
     maus
    0.45
    POSITIVE LOGITS
    纤维
    0.46
    વેશ
    0.45
     pulverized
    0.41
     anastom
    0.41
     imidazole
    0.38
     decomposed
    0.38
     hym
    0.38
     Unsere
    0.37
    拖
    0.37
     Ordered
    0.36
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.