© 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. 78907
    Prev
    Next
    INDEX
    Explanations

    gear indicator

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

    building systems and impact

    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
    :...
    0.54
     എന്നു
    0.50
     welds
    0.47
     чыныгы
    0.47
     ఇక
    0.46
    ilità
    0.46
     selling
    0.46
    Marshaler
    0.45
    нил
    0.45
    lenül
    0.44
    POSITIVE LOGITS
    課程
    0.48
    بي
    0.48
    ما
    0.47
    taking
    0.46
    부
    0.46
     prend
    0.45
    mination
    0.45
    concentration
    0.45
    sab
    0.44
    蠵
    0.44
    Activations Density 0.000%

    No Known Activations