© 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. 57154
    Prev
    Next
    INDEX
    Explanations

    function/contextual phrase components

    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
    irrah
    0.49
    枒
    0.46
    आत्म
    0.46
     nibb
    0.45
     stopwords
    0.44
    ഗ്രഹം
    0.44
     hij
    0.44
    षे
    0.44
    牯
    0.43
    Sure
    0.42
    POSITIVE LOGITS
     እስከ
    0.44
     克
    0.39
     capaz
    0.38
     отдыха
    0.38
     크
    0.38
    ной
    0.38
     तक
    0.37
    例如
    0.37
    ين
    0.36
     salient
    0.36
    Activations Density 0.005%

    No Known Activations