© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 14553
    Prev
    Next
    INDEX
    Explanations

    listing next steps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PBC
    1.32
    *'
    1.28
    indul
    1.27
    PL
    1.25
    ’
    1.24
    melding
    1.23
    ПУ
    1.21
    jelen
    1.21
    XP
    1.21
    rées
    1.20
    POSITIVE LOGITS
     vip
    1.46
     phenotype
    1.43
     Armand
    1.39
     Tyre
    1.37
     कृष्णा
    1.37
     oliva
    1.36
     ANOVA
    1.36
     Wool
    1.35
     吴
    1.34
     Jasmin
    1.31
    Activations Density 0.052%

    No Known Activations