© 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. 58407
    Prev
    Next
    INDEX
    Explanations

    combinatorial and trivial cases

    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
    stranger
    -0.76
    createTextNode
    -0.73
    вами
    -0.72
    Stranger
    -0.69
     Romantic
    -0.68
    Ding
    -0.67
     educativa
    -0.67
    Caroline
    -0.67
     Rat
    -0.66
    会の
    -0.66
    POSITIVE LOGITS
     Pursuit
    1.23
     pursuits
    1.05
     pursuit
    1.05
    APIC
    0.91
    vial
    0.77
    歲
    0.74
    owners
    0.74
     Juris
    0.72
    matics
    0.71
    matters
    0.71
    Activations Density 0.039%

    No Known Activations