© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 6032
    Prev
    Next
    INDEX
    Explanations

    cities and teams

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Specification
    0.46
     funzione
    0.44
     Calyce
    0.43
     Painlev
    0.42
     Peptide
    0.42
     peptide
    0.41
    imgInit
    0.41
    ጷ
    0.41
     Methoden
    0.41
     cellulose
    0.40
    POSITIVE LOGITS
     Atlanta
    1.23
     Philadelphia
    1.09
     Chicago
    1.05
    Atlanta
    1.05
     Boston
    1.04
     Detroit
    1.04
     Celtics
    1.04
     Denver
    1.03
     Tampa
    1.02
     Lakers
    1.00
    Activations Density 0.006%

    No Known Activations