© 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. 15775
    Prev
    Next
    INDEX
    Explanations

    Old Masters (Alte Meister)

    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
    тря
    0.44
     ब्यूरो
    0.42
    刺激
    0.41
     padrões
    0.41
     tremendous
    0.39
    追求
    0.39
    ត្រូ
    0.39
    𝗇
    0.39
     gorgeous
    0.38
     पैकेज
    0.38
    POSITIVE LOGITS
     oil
    0.44
     moral
    0.44
    oil
    0.43
     cat
    0.43
     determinante
    0.41
    bis
    0.41
     whereabouts
    0.41
     huile
    0.41
    brid
    0.40
    male
    0.39
    Activations Density 0.001%

    No Known Activations