© 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. 3606
    Prev
    Next
    INDEX
    Explanations

    url paths and specific words

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

    package or library names

    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
     the
    0.53
     in
    0.49
    7
    0.47
     E
    0.47
     Ch
    0.46
    _
    0.46
     K
    0.46
    2
    0.46
     In
    0.46
    ,
    0.45
    POSITIVE LOGITS
    ᓯ
    0.43
     আনুশকা
    0.39
     পরেও
    0.38
    ফস
    0.37
    <unused98>
    0.36
     trous
    0.36
    মনসিংহ
    0.35
    শিকান্ত
    0.35
    ктак
    0.35
    眝
    0.35
    Activations Density 0.000%

    No Known Activations