© 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. 102006
    Prev
    Next
    INDEX
    Explanations

    consumer rights

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

    they have limitations

    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
    മുണ്ട
    0.50
    ៖
    0.48
    йи
    0.47
    ْن
    0.46
    но
    0.45
    ש
    0.45
    ਦਾ
    0.45
    ദ്
    0.45
    я
    0.45
    دد
    0.44
    POSITIVE LOGITS
     JL
    0.52
     Vogue
    0.45
    <0x9E>
    0.45
     affectionately
    0.45
     MQ
    0.43
     WL
    0.42
     journaling
    0.42
     pequeña
    0.42
     quietly
    0.42
     LJ
    0.42
    Activations Density 0.000%

    No Known Activations