© 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. 30635
    Prev
    Next
    INDEX
    Explanations

    body and intensity descriptors

    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
    ăng
    -0.73
     ihrer
    -0.73
    受講
    -0.67
     reactant
    -0.66
    urement
    -0.65
     Loren
    -0.65
    omon
    -0.64
    dział
    -0.63
    recht
    -0.63
     když
    -0.63
    POSITIVE LOGITS
     body
    4.06
    body
    3.27
     Body
    3.13
    Body
    3.08
     bodied
    3.06
     BODY
    2.94
    BODY
    2.81
    bodied
    2.67
     bodies
    2.66
     cuerpo
    2.64
    Activations Density 0.028%

    No Known Activations