© 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. 30749
    Prev
    Next
    INDEX
    Explanations

    license headers and comments

    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
     Julien
    -0.73
    Hug
    -0.70
    гант
    -0.68
    gown
    -0.68
    smile
    -0.66
     wiedzy
    -0.66
     BOND
    -0.65
    vių
    -0.65
    tume
    -0.64
    Julien
    -0.63
    POSITIVE LOGITS
     beitragen
    0.69
     electrical
    0.68
    idon
    0.65
     自
    0.64
    ekte
    0.64
    タブレット
    0.64
    셈
    0.63
    ₅
    0.63
     pomiesz
    0.63
     graphics
    0.62
    Activations Density 0.111%

    No Known Activations