© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 30364
    Prev
    Next
    INDEX
    Explanations

    matching patterns and filenames

    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
    ir
    0.53
     I
    0.47
     JOUR
    0.45
     Schulen
    0.43
     entsch
    0.43
    h
    0.43
     SERVICE
    0.42
    l
    0.42
    ac
    0.42
    PRE
    0.42
    POSITIVE LOGITS
     polinom
    0.49
     بدور
    0.48
    ূল্য
    0.48
     مذہ
    0.47
    さが
    0.47
     моно
    0.46
     величина
    0.45
     possono
    0.45
     потребуется
    0.45
     метода
    0.44
    Activations Density 0.002%

    No Known Activations