© 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. 26195
    Prev
    Next
    INDEX
    Explanations

    familiarity and skill gained

    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
    zeli
    -0.99
     strumenti
    -0.90
     obiettivi
    -0.86
     cristianismo
    -0.86
     phận
    -0.86
     '../../../../
    -0.85
     nothing
    -0.85
     esfuerzo
    -0.82
     teclas
    -0.82
    そのまま
    -0.82
    POSITIVE LOGITS
     better
    1.19
     familiarity
    1.15
    숙
    1.13
     hvor
    1.09
    谙
    1.07
     know
    1.05
     learned
    1.03
     learns
    1.02
     learnt
    1.01
     bättre
    1.00
    Activations Density 0.030%

    No Known Activations