© 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. 93138
    Prev
    Next
    INDEX
    Explanations

    early and personal life

    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
    ,
    -1.38
     but
    -1.20
    ca
    -1.18
     V
    -1.17
     M
    -1.17
    ce
    -1.15
     L
    -1.13
    fe
    -1.13
     C
    -1.13
    te
    -1.13
    POSITIVE LOGITS
    ↵↵
    1.77
    ↵
    1.73
    pekte
    1.34
     kabát
    1.28
    Mvh
    1.27
     tunik
    1.27
     keramik
    1.26
    Öl
    1.25
     repuesto
    1.22
     desblo
    1.19
    Activations Density 0.061%

    No Known Activations