© 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. 100615
    Prev
    Next
    INDEX
    Explanations

    specific content following keywords

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

    recipient understanding

    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
     funções
    0.50
     océ
    0.50
    <0xB2>
    0.48
     ছয়
    0.47
     judge
    0.47
     greet
    0.47
     yarg
    0.47
     断
    0.47
    <0xAE>
    0.46
     funciones
    0.45
    POSITIVE LOGITS
    pleasant
    0.52
    ST
    0.51
    life
    0.47
    KON
    0.47
    UU
    0.47
    household
    0.47
    itel
    0.46
     معاملہ
    0.46
    MRT
    0.46
     itse
    0.46
    Activations Density 0.000%

    No Known Activations