© 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. 210980
    Prev
    Next
    INDEX
    Explanations

    variations including

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

    purpose, reason, context

    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
    一份
    0.41
    ATS
    0.41
     ramifications
    0.38
    birthday
    0.38
     поча
    0.38
     与
    0.38
     वंश
    0.38
    取
    0.38
    Birthday
    0.37
    MotionEvent
    0.37
    POSITIVE LOGITS
     infallible
    0.40
    lüsse
    0.38
    ամ
    0.38
    ष्टी
    0.38
     Connie
    0.37
    ঃখ
    0.37
     najbardziej
    0.37
    㖩
    0.36
    工艺
    0.36
     pund
    0.35
    Activations Density 0.000%

    No Known Activations