© 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. 124108
    Prev
    Next
    INDEX
    Explanations

    discussion, amount, continuously

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

    responsible for

    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
    ively
    0.45
     Jee
    0.45
     गणपति
    0.45
     stalwart
    0.44
    heath
    0.44
     Healy
    0.44
     sixty
    0.43
     ઉ
    0.43
    encoded
    0.42
    authorization
    0.42
    POSITIVE LOGITS
    وعه
    0.52
    ж
    0.51
    ськ
    0.50
    ج
    0.50
    艨
    0.50
    ഷ്ണ
    0.48
     formu
    0.47
    ונ
    0.46
    ଛ
    0.46
    刊
    0.46
    Activations Density 0.000%

    No Known Activations