© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 46741
    Prev
    Next
    INDEX
    Explanations

    list items being specified

    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
    t
    0.68
    R
    0.56
    et
    0.52
    高度
    0.51
    a
    0.50
    add
    0.50
    j
    0.49
    Highly
    0.48
    am
    0.47
    2
    0.47
    POSITIVE LOGITS
    纮
    0.47
     glaring
    0.47
    ⇰
    0.46
     방법에
    0.46
     foodstuffs
    0.45
     swamps
    0.45
     Binder
    0.45
    ꫝ
    0.44
     mates
    0.43
    वेल
    0.43
    Activations Density 0.000%

    No Known Activations