© 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. 78789
    Prev
    Next
    INDEX
    Explanations

    scope creep, optical device, equipped rifle

    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
    щики
    -0.86
    studios
    -0.86
     Совета
    -0.77
    øy
    -0.76
    biz
    -0.75
    ƈ
    -0.74
    bior
    -0.73
    сихо
    -0.73
    eacute
    -0.71
     Ruling
    -0.71
    POSITIVE LOGITS
     lenses
    1.22
     parallax
    1.20
     turrets
    1.11
     lens
    1.09
     clarity
    1.08
     turret
    1.05
     magnification
    1.01
     scopes
    0.93
     ocular
    0.92
    ocular
    0.89
    Activations Density 0.002%

    No Known Activations