© 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. 4008
    Prev
    Next
    INDEX
    Explanations

    and generate

    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
     sechs
    0.40
     six
    0.39
     trzech
    0.38
    six
    0.37
    <unused36>
    0.37
     trzy
    0.36
     seis
    0.36
     הנ
    0.35
    ᑯ
    0.35
     trei
    0.35
    POSITIVE LOGITS
    线下
    0.39
    itu
    0.38
    createText
    0.38
    json
    0.36
     Shalom
    0.35
    かって
    0.35
     ude
    0.35
    DB
    0.34
    yo
    0.34
    ங்களில்
    0.34
    Activations Density 0.012%

    No Known Activations