© 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. 217771
    Prev
    Next
    INDEX
    Explanations

    is followed by equal or and

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

    specifications and categories

    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
    kwargs
    0.55
    PP
    0.50
    to
    0.48
    dj
    0.45
    -
    0.45
    personas
    0.43
    ()'
    0.43
    tour
    0.43
    essential
    0.43
    tt
    0.43
    POSITIVE LOGITS
     improb
    0.50
     Mahindra
    0.49
     disband
    0.47
     Mahama
    0.46
     abstinence
    0.46
     GoName
    0.46
     nee
    0.45
    䢀
    0.45
     manhã
    0.44
    疃
    0.44
    Activations Density 0.001%

    No Known Activations