© 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. 138672
    Prev
    Next
    INDEX
    Explanations

    physically crush, Claude 3 Opus, Old Man Tiber

    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
     niem
    0.49
    🎱
    0.49
    াদেশিক
    0.47
    ronique
    0.46
     নগ
    0.46
     Ча
    0.46
     নৌ
    0.45
     Ро
    0.45
     Ger
    0.44
    <unused18>
    0.43
    POSITIVE LOGITS
    ع
    0.58
    هم
    0.58
    ست
    0.54
    ق
    0.52
    P
    0.49
    b
    0.48
    د
    0.47
    ک
    0.46
    ش
    0.46
    o
    0.45
    Activations Density 0.001%

    No Known Activations