© 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. 16-GEMMASCOPE-2-RES-262K
    7. 40724
    Prev
    Next
    INDEX
    Explanations

    identifying predecessors

    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_16_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
    c
    0.95
    あります
    0.92
    り
    0.92
     પછી
    0.90
    tting
    0.90
    𝕚
    0.88
     be
    0.88
    言う
    0.88
    ется
    0.87
     obrig
    0.86
    POSITIVE LOGITS
    ’
    1.33
     successor
    1.19
     successors
    1.18
     predecessor
    1.07
    */
    1.03
    successor
    0.99
     predecessors
    0.98
    Α
    0.93
     (
    0.91
    √
    0.83
    Activations Density 0.003%

    No Known Activations