© 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. 53080
    Prev
    Next
    INDEX
    Explanations

    wealth accumulation, scripts, eunuchs

    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
     Kode
    0.49
    剧
    0.48
     kode
    0.48
     procédé
    0.47
     Acre
    0.46
    标
    0.43
    Kode
    0.43
     Nä
    0.43
    码
    0.43
     Após
    0.43
    POSITIVE LOGITS
    savings
    0.46
    recognition
    0.46
    gruntled
    0.43
    𝟬
    0.43
    rous
    0.42
    უქ
    0.42
    esistenza
    0.42
    rying
    0.41
    mentioned
    0.41
    assuming
    0.41
    Activations Density 0.014%

    No Known Activations