© 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. 14455
    Prev
    Next
    INDEX
    Explanations

    penalty and penalize

    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
    밂
    0.96
     vattum
    0.95
    쭈
    0.91
    욀
    0.89
    퍁
    0.89
    routingHeader
    0.89
    elementProp
    0.89
     길이가
    0.88
     rbuf
    0.87
    캿
    0.86
    POSITIVE LOGITS
     and
    1.27
    .
    1.15
    and
    1.13
    <0xF3>
    1.13
    This
    1.13
     of
    1.12
    The
    1.11
    It
    1.10
     It
    1.05
     This
    1.04
    Activations Density 0.003%

    No Known Activations