© 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-65K
    7. 7683
    Prev
    Next
    INDEX
    Explanations

    conditions before or after

    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_65k_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
    ）：
    0.50
    क्तिक
    0.50
    ating
    0.48
    ۹
    0.47
    istance
    0.46
    nungen
    0.46
    creen
    0.46
    日間
    0.46
    خ
    0.46
    ទ
    0.46
    POSITIVE LOGITS
     supply
    0.50
     taught
    0.47
     triang
    0.44
     parametrization
    0.43
     triplet
    0.43
    taught
    0.43
     surm
    0.43
     guessed
    0.43
     ambiguity
    0.42
    Indianapolis
    0.42
    Activations Density 0.018%

    No Known Activations