© 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. 137375
    Prev
    Next
    INDEX
    Explanations

    search for a

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

    speedrunning or range extender

    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
     mano
    0.47
    ک
    0.46
    `/
    0.46
    ار
    0.45
    切り
    0.45
    の位置
    0.45
    mios
    0.44
     mediocr
    0.43
    ح
    0.42
     mencionado
    0.42
    POSITIVE LOGITS
     పార్టీ
    0.52
    <unused2200>
    0.47
     treasury
    0.46
     వాటి
    0.45
    ahead
    0.45
     전달
    0.44
    కుంది
    0.44
    Bei
    0.44
     পরিবহ
    0.44
     생성
    0.43
    Activations Density 0.000%

    No Known Activations