© 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. 22-GEMMASCOPE-RES-131K
    7. 128778
    Prev
    Next
    INDEX
    Explanations

    factor and target

    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_22/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
     heilige
    -1.27
     pioneers
    -1.13
     superbes
    -1.09
     flotte
    -1.07
     Heilige
    -1.05
     kanker
    -1.05
     ideale
    -1.04
     atmosfera
    -1.04
     olvido
    -1.03
    figuren
    -1.03
    POSITIVE LOGITS
     we
    1.40
     with
    1.20
     this
    1.04
    世上
    1.03
     there
    1.02
     acknowledging
    1.00
     now
    0.97
     únicamente
    0.96
    G
    0.95
     our
    0.94
    Activations Density 0.001%

    No Known Activations