© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49357
    Prev
    Next
    INDEX
    Explanations

    behind

    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
    avoit
    -0.94
    entran
    -0.79
    chá
    -0.74
    ACIO
    -0.73
     サッカー
    -0.73
    dech
    -0.73
     kwar
    -0.73
    glich
    -0.71
    archical
    -0.71
     naira
    -0.71
    POSITIVE LOGITS
     behind
    5.53
    behind
    4.06
    Behind
    3.92
     Behind
    3.80
     detrás
    2.92
     BEHIND
    2.91
     derrière
    2.84
     dietro
    2.58
     پشت
    2.45
     bakom
    2.28
    Activations Density 0.034%

    No Known Activations