© 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. 61290
    Prev
    Next
    INDEX
    Explanations

    It is

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

    requires

    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
     партнер
    0.46
     वैश्विक
    0.45
     sabbatical
    0.45
     විශේෂ
    0.44
     න
    0.44
     എല്ലാ
    0.43
    Bsky
    0.43
     مختلف
    0.43
     પ
    0.43
    <unused2004>
    0.43
    POSITIVE LOGITS
    nSamples
    0.46
    imientos
    0.45
     soff
    0.43
    ক্ষম
    0.42
    下來
    0.42
    ând
    0.41
    ์
    0.41
    বাড়
    0.41
    ípios
    0.40
     ô
    0.40
    Activations Density 0.001%

    No Known Activations