© 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. 165779
    Prev
    Next
    INDEX
    Explanations

    accurate representation and results

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

    research and analysis structure

    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
    詄
    0.55
    璺
    0.51
     textil
    0.50
     الفرنسي
    0.49
    RationalValue
    0.48
     Airt
    0.48
    ılabilir
    0.47
     poz
    0.47
     Bewert
    0.47
     béton
    0.47
    POSITIVE LOGITS
    s
    0.61
    mama
    0.53
    come
    0.49
    interno
    0.49
    error
    0.48
    prior
    0.47
    age
    0.46
    ia
    0.46
    probabilities
    0.46
    ense
    0.46
    Activations Density 0.000%

    No Known Activations