© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14490
    Prev
    Next
    INDEX
    Explanations

    game, event, team, role, member, pay, heart

    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
     first
    -1.13
     after
    -1.11
     decreased
    -1.09
     giving
    -1.06
     avoiding
    -1.05
     acknowledging
    -1.05
     only
    -1.05
     from
    -1.04
     creating
    -1.02
     give
    -1.02
    POSITIVE LOGITS
    rout
    1.05
     eral
    1.05
    recently
    1.03
    の方に
    1.02
     LARGE
    1.01
    might
    1.00
     Ê
    0.99
     vijf
    0.99
    際に
    0.98
     LIGHT
    0.98
    Activations Density 0.104%

    No Known Activations