© 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. 836
    Prev
    Next
    INDEX
    Explanations

    integers, comprehension, 4bit

    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
    ون
    0.62
    א
    0.59
     It
    0.56
    ח
    0.55
    ين
    0.55
    ש
    0.54
    ان
    0.53
    ాన్ని
    0.52
    스
    0.52
    arbe
    0.50
    POSITIVE LOGITS
    0.64
    ний
    0.56
    )))
    0.48
     marzo
    0.47
    ᓛ
    0.46
     erano
    0.46
     feitos
    0.45
     ruas
    0.44
    9
    0.44
    й
    0.44
    Activations Density 0.525%

    No Known Activations