© 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-IT
    5. 13-GEMMASCOPE-2-RES-65K
    7. 1341
    Prev
    Next
    INDEX
    Explanations

    fatty core

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    1.24
     열심히
    1.21
     şeklinde
    1.12
    లె
    1.09
     peł
    1.09
     další
    1.08
     약간
    1.08
     svom
    1.07
     반
    1.07
     루
    1.07
    POSITIVE LOGITS
    ness
    2.18
    NESS
    1.47
    nesses
    1.26
    eness
    1.20
    nesse
    1.16
    তায়
    1.14
     substances
    1.13
    nese
    1.12
    est
    1.12
     materials
    1.10
    Activations Density 2.266%

    No Known Activations