© 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. 64076
    Prev
    Next
    INDEX
    Explanations

    Given

    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
    理
    -0.73
    wars
    -0.72
    dores
    -0.66
    awards
    -0.64
    Fotó
    -0.64
     Надо
    -0.63
     לי
    -0.63
     sampling
    -0.62
    Alphabet
    -0.62
    してない
    -0.61
    POSITIVE LOGITS
     Given
    1.29
    Given
    1.22
     step
    1.20
     then
    1.17
     steps
    1.12
     feature
    1.07
     given
    1.06
    gher
    1.06
     GIVEN
    1.05
    Step
    1.02
    Activations Density 0.043%

    No Known Activations