© 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-65K
    7. 63778
    Prev
    Next
    INDEX
    Explanations

    used, not, deep dive

    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_65k_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
    antium
    0.47
    Variable
    0.44
    azawa
    0.44
    static
    0.43
    :(
    0.42
     (
    0.41
    <
    0.41
    var
    0.41
    /
    0.41
    requent
    0.40
    POSITIVE LOGITS
     élarg
    0.56
     הב
    0.55
     подчи
    0.54
     czyli
    0.50
     języ
    0.49
     نیوز
    0.48
    ニュース
    0.48
     ದೊಡ್ಡ
    0.46
     క్యా
    0.45
     психи
    0.45
    Activations Density 0.001%

    No Known Activations