© 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. 31739
    Prev
    Next
    INDEX
    Explanations

    numbers following specific model names

    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
     the
    -1.07
     decided
    -0.96
     And
    -0.95
     told
    -0.94
    ようです
    -0.91
    ようだ
    -0.90
     akibat
    -0.88
    "
    -0.88
     something
    -0.88
    こともある
    -0.86
    POSITIVE LOGITS
     tirs
    1.20
    Lalu
    1.06
     MINE
    0.98
     COMPOUNDS
    0.98
    COMO
    0.98
     ć
    0.96
     SIGNIFIC
    0.96
     spesial
    0.95
    layın
    0.95
    してます
    0.95
    Activations Density 0.059%

    No Known Activations