© 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. 11551
    Prev
    Next
    INDEX
    Explanations

    transformation

    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
    are
    1.59
    of
    1.55
    6
    1.39
    ی
    1.38
    1
    1.33
    ای
    1.27
    AL
    1.23
     is
    1.21
    ра
    1.09
    ка
    1.09
    POSITIVE LOGITS
    ก
    1.45
    ر
    1.40
     I
    1.30
     can
    1.19
    ض
    1.19
     metamorph
    1.17
    ם
    1.17
     transforms
    1.15
    มัน
    1.13
    ר
    1.09
    Activations Density 0.028%

    No Known Activations