© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 201597
    Prev
    Next
    INDEX
    Explanations

    languages and specific entities

    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
    v
    0.65
    t
    0.57
    s
    0.57
    e
    0.56
    u
    0.55
    b
    0.54
    r
    0.52
    f
    0.51
    w
    0.50
    i
    0.50
    POSITIVE LOGITS
     profondeur
    0.56
    睄
    0.54
    GTUIKit
    0.53
     nawet
    0.51
     ภาษา
    0.51
     synagogue
    0.50
     Sprachen
    0.50
     regelmatig
    0.49
     erős
    0.49
     গভীর
    0.49
    Activations Density 0.001%

    No Known Activations