© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 165230
    Prev
    Next
    INDEX
    Explanations

    what is size headlines subtitle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
     Aseg
    0.44
    偿
    0.40
     रीति
    0.40
     Enlarg
    0.39
    addSql
    0.38
     расходы
    0.38
     slaughter
    0.38
    饰
    0.38
     recovered
    0.37
     ornaments
    0.37
    POSITIVE LOGITS
    independent
    0.46
     koska
    0.40
    arks
    0.40
    illis
    0.39
    ｒ
    0.37
    Independent
    0.36
    athermy
    0.36
     Independent
    0.36
     NASA
    0.35
    "="
    0.35
    Activations Density 0.001%

    No Known Activations