© 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. 209371
    Prev
    Next
    INDEX
    Explanations

    day distribution

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

    language transition

    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
    stub
    0.45
    搀
    0.45
     stets
    0.43
     జ్ఞ
    0.42
    dictionary
    0.41
    grond
    0.41
    ເກ
    0.40
    lässlich
    0.40
    ضبط
    0.39
    reactor
    0.39
    POSITIVE LOGITS
    جے
    0.49
    ór
    0.43
    মি
    0.43
     वहीं
    0.43
    त्ति
    0.43
    यण
    0.42
     速
    0.42
    ན་
    0.41
     મળી
    0.41
     शुगर
    0.41
    Activations Density 0.003%

    No Known Activations