© 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. 223472
    Prev
    Next
    INDEX
    Explanations

    words before common follow-ups

    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
     werkt
    0.40
    ूड
    0.40
    ម្ត
    0.40
    ->$
    0.38
    녈
    0.38
    횟
    0.38
     ond
    0.37
    WER
    0.37
    Worked
    0.37
    ->
    0.36
    POSITIVE LOGITS
    ciparum
    0.43
    多分
    0.40
    ultures
    0.39
     u
    0.38
     &=\
    0.37
    的部分
    0.36
     quizás
    0.36
     Schwartz
    0.36
    agoza
    0.36
     Voices
    0.35
    Activations Density 0.000%

    No Known Activations