© 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. 196807
    Prev
    Next
    INDEX
    Explanations

    get help

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

    Larger Conventional wars, Generative AI, Intent, CentOS, fees

    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
     EEOC
    0.47
     FSA
    0.47
    擀
    0.46
    容易
    0.46
     présent
    0.46
     Kay
    0.46
    蛋糕
    0.45
     BMX
    0.45
     EEA
    0.44
     NGO
    0.44
    POSITIVE LOGITS
    پل
    0.55
    ת
    0.53
     фанта
    0.49
    ிரம்
    0.47
    TimeDict
    0.46
    FixedWidth
    0.45
    ैन
    0.45
    serializer
    0.45
    PL
    0.45
    StructOf
    0.45
    Activations Density 0.000%

    No Known Activations