© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 40282
    Prev
    Next
    INDEX
    Explanations

    consent, mir, 6

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

    ```details```

    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
    up
    0.48
    that
    0.47
    提前
    0.44
    without
    0.44
    っ
    0.43
    crollView
    0.43
    p
    0.43
    ini
    0.42
    with
    0.42
    完了
    0.42
    POSITIVE LOGITS
     Erschein
    0.50
    ﹡
    0.50
     meisten
    0.49
    ضان
    0.48
     Dose
    0.48
     meeste
    0.48
     ontwikkeling
    0.46
     angegeben
    0.46
    龈
    0.45
    ParamNum
    0.45
    Activations Density 0.001%

    No Known Activations