© 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. 44451
    Prev
    Next
    INDEX
    Explanations

    okay or cool too

    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
    desPort
    0.45
    setBadge
    0.42
    পালা
    0.42
    ሰ
    0.41
    ዳ
    0.41
    隐藏
    0.41
    timelist
    0.41
    medallas
    0.40
    ག
    0.40
    Dining
    0.40
    POSITIVE LOGITS
     tested
    0.50
    pon
    0.46
    ana
    0.46
    er
    0.46
     use
    0.45
    ia
    0.45
    al
    0.44
     productive
    0.42
    ing
    0.42
    t
    0.42
    Activations Density 0.003%

    No Known Activations