© 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. 60614
    Prev
    Next
    INDEX
    Explanations

    approaching winter and aid

    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
    溘
    0.47
     Redeemer
    0.46
     this
    0.45
     total
    0.44
     Climb
    0.44
     centres
    0.43
    تي
    0.43
    怆
    0.43
     في
    0.42
     climbing
    0.42
    POSITIVE LOGITS
    Sheikh
    0.55
    いろんな
    0.51
    HAHA
    0.49
    arabic
    0.48
    avak
    0.48
    ׁ
    0.48
    kafka
    0.48
    сказа
    0.48
    edik
    0.46
    ukh
    0.46
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.