© 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. 13-GEMMASCOPE-2-RES-16K
    7. 8984
    Prev
    Next
    INDEX
    Explanations

    plays a role or importance

    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_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
    itonitis
    1.22
    ബന്ധ
    1.05
     Bost
    0.97
    انوں
    0.96
    terminated
    0.94
    lok
    0.94
    ล่า
    0.92
    a
    0.90
    uces
    0.88
    রাম
    0.88
    POSITIVE LOGITS
     role
    2.12
     роль
    2.03
     ROLE
    2.03
     Role
    1.98
     rôle
    1.98
     ruolo
    1.93
     역할
    1.92
    Role
    1.92
    ROLE
    1.90
     roles
    1.89
    Activations Density 0.158%

    No Known Activations