Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 15009
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
     &
    1.46
    \&
    1.38
    &
    1.38
    n
    1.30
    アンド
    1.30
     \&
    1.30
    ל
    1.26
     పాటు
    1.23
    a
    1.19
    u
    1.15
    POSITIVE LOGITS
     Violent
    1.56
     resistencia
    1.55
     gestire
    1.54
     neonatal
    1.54
     increíble
    1.53
     nefarious
    1.53
     vivienda
    1.52
     Salford
    1.50
     funcionalidades
    1.49
     violent
    1.46
    Activations Density 0.022%

    No Known Activations