© 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. 123532
    Prev
    Next
    INDEX
    Explanations

    groups, situations, or challenges

    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
    સ
    0.48
    ש
    0.48
    শ
    0.47
    ვ
    0.45
    すぎて
    0.43
     lofty
    0.43
    بي
    0.42
    量子
    0.42
    م
    0.42
     mutants
    0.41
    POSITIVE LOGITS
     Trabajo
    0.51
     trabajador
    0.47
    💟
    0.47
    RENGTH
    0.46
    🚱
    0.44
     alfabet
    0.44
    📪
    0.44
     обще
    0.42
     रोजगार
    0.42
     haga
    0.42
    Activations Density 0.008%

    No Known Activations