© 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. 93345
    Prev
    Next
    INDEX
    Explanations

    shadow

    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
     Ansprechpartner
    -0.91
     calefacción
    -0.84
     ulub
    -0.77
     altavoz
    -0.75
     reemplazo
    -0.75
     Cast
    -0.75
    ₨
    -0.74
     zatem
    -0.73
     polizia
    -0.73
    ensk
    -0.72
    POSITIVE LOGITS
     shadow
    1.01
     Shadow
    0.86
     shadows
    0.85
    Shadow
    0.83
    shadow
    0.83
     SHADOW
    0.76
    elevation
    0.75
    SHADOW
    0.75
    образ
    0.74
     CMOS
    0.73
    Activations Density 0.001%

    No Known Activations