© 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. 197597
    Prev
    Next
    INDEX
    Explanations

    reporting factual information

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

    its generation

    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
     STADT
    0.52
    ')";
    0.50
    இந்த
    0.48
     интерес
    0.47
     CENTRE
    0.46
     проблем
    0.46
     CHILDREN
    0.45
    tAux
    0.45
     другое
    0.45
     теннис
    0.45
    POSITIVE LOGITS
     النج
    0.47
     کر
    0.42
     رأ
    0.41
     र
    0.40
    ্লো
    0.40
     Gone
    0.40
     فى
    0.39
     रोक
    0.39
    deposited
    0.39
     rollover
    0.39
    Activations Density 0.001%

    No Known Activations