© 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. 240950
    Prev
    Next
    INDEX
    Explanations

    states or contexts

    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
     parenchyma
    0.53
    iculation
    0.48
    abbanti
    0.48
     anhydride
    0.48
     вступи
    0.47
     մաս
    0.47
     backpacking
    0.46
    溟
    0.46
     परिष
    0.46
    नातील
    0.46
    POSITIVE LOGITS
    a
    0.53
    k
    0.52
    z
    0.50
    ه
    0.49
    ENV
    0.48
    response
    0.47
     enviado
    0.46
     stabile
    0.46
     Secretaria
    0.46
    b
    0.46
    Activations Density 0.000%

    No Known Activations