© 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-3-270M-IT
    5. 15-GEMMASCOPE-2-RES-262K
    7. 69849
    Prev
    Next
    INDEX
    Explanations

    I state intentions or actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_15_width_262k_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
     /
    1.22
     of
    1.19
     also
    1.14
     i
    1.12
    RT
    1.12
    !
    1.11
     >
    1.10
     continue
    1.10
    .
    1.10
     Translated
    1.09
    POSITIVE LOGITS
     salesmen
    1.78
    nią
    1.77
    飩
    1.68
    噱
    1.66
    owntown
    1.66
     автоматы
    1.65
    avro
    1.51
     salespeople
    1.49
     cvec
    1.49
    CLUDING
    1.45
    Activations Density 0.001%

    No Known Activations