© 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. 117576
    Prev
    Next
    INDEX
    Explanations

    bait and program

    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
    rostis
    -0.77
    松山
    -0.77
    ideen
    -0.74
    屋敷
    -0.69
     poš
    -0.68
     atlet
    -0.67
    })^
    -0.67
    رایش
    -0.67
    khid
    -0.65
     évêque
    -0.65
    POSITIVE LOGITS
     < 
    0.80
     Single
    0.78
    piro
    0.74
     ưu
    0.73
     agencia
    0.71
    tigen
    0.70
     Declare
    0.69
    working
    0.68
    necessary
    0.68
    prior
    0.68
    Activations Density 0.055%

    No Known Activations