© 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. 117633
    Prev
    Next
    INDEX
    Explanations

    novel, time, game, texts

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

    crime and punishment summary

    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
    c
    0.58
    nél
    0.52
     बैठे
    0.52
    cS
    0.47
     الوزراء
    0.46
    cJ
    0.46
    llo
    0.46
     ஒவ்வ
    0.45
    h
    0.45
    g
    0.45
    POSITIVE LOGITS
    "
    0.56
    /*
    0.49
    är
    0.49
     /*
    0.49
    ีน
    0.46
    2
    0.45
    认为
    0.44
    ReaderWriter
    0.44
    ΗΣ
    0.44
    ινό
    0.44
    Activations Density 0.000%

    No Known Activations