© 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. 45185
    Prev
    Next
    INDEX
    Explanations

    citations needed

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

    grill marks

    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
     vocab
    0.47
     leer
    0.47
    婇
    0.47
     ちゃう
    0.46
     नेत
    0.46
     또
    0.45
     دہ
    0.45
     componente
    0.45
     μορ
    0.45
     इच्छ
    0.44
    POSITIVE LOGITS
    _
    0.55
    ng
    0.52
    logo
    0.50
    k
    0.48
    null
    0.48
    군
    0.48
    ที่สุด
    0.47
    <0xE3>
    0.46
     null
    0.46
    ngr
    0.46
    Activations Density 0.001%

    No Known Activations