© 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. 79735
    Prev
    Next
    INDEX
    Explanations

    free media access

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

    a bit of a challenge

    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
     Gwyn
    0.47
     وم
    0.44
     Badger
    0.44
     மறு
    0.43
     対
    0.43
     ب
    0.43
     السماء
    0.43
    叢
    0.43
     Salmon
    0.42
     ½
    0.42
    POSITIVE LOGITS
    тні
    0.53
    रील
    0.51
    RENT
    0.50
    pH
    0.49
    यात्रा
    0.48
    ये
    0.48
    NORTH
    0.48
    WAY
    0.47
    HNO
    0.46
    cold
    0.46
    Activations Density 0.001%

    No Known Activations