© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78396
    Prev
    Next
    INDEX
    Explanations

    SPDX license identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     profoundly
    -0.83
    acos
    -0.82
     аксессу
    -0.81
    ❧
    -0.81
    著者
    -0.81
    一の
    -0.80
     AWESOME
    -0.80
    Они
    -0.79
     reflexive
    -0.79
     any
    -0.76
    POSITIVE LOGITS
    ,;
    0.87
    tep
    0.82
     ด
    0.81
     PMC
    0.81
    cle
    0.81
    ;&
    0.80
     мое
    0.79
     atualmente
    0.77
     CREDIT
    0.75
    LLING
    0.75
    Activations Density 0.002%

    No Known Activations