© 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. 31814
    Prev
    Next
    INDEX
    Explanations

    german ui previews

    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
    hitth
    0.62
    man
    0.61
    men
    0.60
    kuat
    0.60
    ier
    0.60
    nhs
    0.59
    btnUn
    0.59
    ႏ
    0.59
    carb
    0.59
    menopausal
    0.59
    POSITIVE LOGITS
    5
    0.64
    ו
    0.64
    9
    0.63
    6
    0.61
    و
    0.59
    8
    0.56
     software
    0.55
    I
    0.54
     earthquake
    0.54
     activities
    0.54
    Activations Density 0.001%

    No Known Activations