© 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. 2616
    Prev
    Next
    INDEX
    Explanations

    malicious use and effects

    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
    -
    2.18
     ,
    2.04
    a
    1.98
    .
    1.97
     в
    1.97
    ed
    1.95
     Х
    1.91
     آ
    1.89
    ,
    1.88
     و
    1.87
    POSITIVE LOGITS
     nombreux
    2.64
     molti
    2.52
     coloro
    2.49
     realizzazione
    2.47
     numerosos
    2.47
     posizione
    2.43
     numerose
    2.41
     equipes
    2.38
     misure
    2.38
     collegamento
    2.37
    Activations Density 0.017%

    No Known Activations