© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 60983
    Prev
    Next
    INDEX
    Explanations

    case assessment, immediate family, more and more

    np_acts-logits-general · gemini-2.5-flash-lite

    skill, honor, belief, or conditional logic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ers
    0.58
    _
    0.57
    ag
    0.52
     different
    0.52
     petroleum
    0.52
    ati
    0.51
     Petroleum
    0.51
    uri
    0.50
    aget
    0.50
    us
    0.49
    POSITIVE LOGITS
    Admiral
    0.48
    декс
    0.47
    KSprite
    0.45
    宪
    0.44
     ۲۰۱
    0.44
    卓越
    0.44
     çıkar
    0.43
    图中
    0.43
    GALAD
    0.42
    赞
    0.42
    Activations Density 0.000%

    No Known Activations