© 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. 31-GEMMASCOPE-2-RES-262K
    7. 32974
    Prev
    Next
    INDEX
    Explanations

    options, response, binary, ordered

    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_31_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
     Battle
    0.48
     Napole
    0.48
     пропор
    0.47
     балан
    0.46
     Kalk
    0.44
     Boga
    0.44
    챱
    0.43
    स्तों
    0.43
     Bald
    0.43
    Impress
    0.42
    POSITIVE LOGITS
    movie
    0.43
    indrome
    0.41
     remove
    0.41
    电影
    0.40
    াদ
    0.39
    チ
    0.38
    歌詞
    0.38
    <tr>
    0.37
     font
    0.37
     shape
    0.37
    Activations Density 0.000%

    No Known Activations