© 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. 111291
    Prev
    Next
    INDEX
    Explanations

    roll against

    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
    <0xE2>
    0.50
    une
    0.49
    are
    0.45
    ig
    0.45
    規格
    0.43
    able
    0.42
     be
    0.42
     use
    0.42
     Une
    0.40
    is
    0.40
    POSITIVE LOGITS
    klı
    0.54
    ogramDetails
    0.54
    3
    0.54
    7
    0.50
     horrified
    0.48
    いくつかの
    0.48
    WMat
    0.48
    ParaName
    0.46
     problemler
    0.46
    িশালী
    0.46
    Activations Density 0.003%

    No Known Activations