© 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. 194587
    Prev
    Next
    INDEX
    Explanations

    unique words and characters

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

    rainforests of the sea, cosmic, Mangalsutra

    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
     coalitions
    0.51
    مپ
    0.50
    軚
    0.50
     rapporti
    0.50
     monde
    0.49
     carreg
    0.49
     clashed
    0.48
    وا
    0.48
     Liaison
    0.47
     materiais
    0.47
    POSITIVE LOGITS
    ukam
    0.50
    KS
    0.48
     उन्‍हें
    0.47
    KEN
    0.47
    ICK
    0.46
    PARAM
    0.46
    𝗡
    0.46
     น้อง
    0.46
     פר
    0.46
    lx
    0.45
    Activations Density 0.000%

    No Known Activations