© 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. 8983
    Prev
    Next
    INDEX
    Explanations

    Baywatch lifeguards and actresses

    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
    .
    1.07
    -
    1.01
    z
    0.99
     guía
    0.99
    vy
    0.86
    ,
    0.86
    …
    0.82
    ınd
    0.80
    ur
    0.80
     and
    0.80
    POSITIVE LOGITS
    ಯಲ್ಲಿ
    1.48
     만족
    1.46
    ycling
    1.46
     삼성
    1.41
     vattum
    1.41
    akkhati
    1.39
    <unused1937>
    1.39
     Pogis
    1.39
    avasena
    1.39
     thermoplastics
    1.37
    Activations Density 0.032%

    No Known Activations