© 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. 106664
    Prev
    Next
    INDEX
    Explanations

    following word context

    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
     отвечает
    -1.00
     what
    -0.92
     vielä
    -0.89
    estacks
    -0.87
     ešte
    -0.86
     already
    -0.85
     Preg
    -0.84
    وائ
    -0.83
    dır
    -0.81
     piemē
    -0.81
    POSITIVE LOGITS
    Em
    0.96
    subtitle
    0.91
     melee
    0.87
    𝑦
    0.86
    _
    0.84
     статус
    0.82
     Dernière
    0.82
     Em
    0.81
    [(
    0.79
    getLong
    0.79
    Activations Density 0.000%

    No Known Activations