© 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. 15845
    Prev
    Next
    INDEX
    Explanations

    arterial, despite, DICT, 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_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
     (
    0.45
    ໄ
    0.44
     trays
    0.42
     cu
    0.39
    ፈል
    0.39
     weir
    0.38
    体に
    0.38
     external
    0.38
    体
    0.38
     parsing
    0.37
    POSITIVE LOGITS
     protegido
    0.45
    ાલુ
    0.42
    মত
    0.41
     выигра
    0.41
     Defendants
    0.40
    ন্যবাদ
    0.40
     этим
    0.38
    ONTAL
    0.38
     этом
    0.38
     этого
    0.38
    Activations Density 0.000%

    No Known Activations