© 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-65K
    7. 61531
    Prev
    Next
    INDEX
    Explanations

    direct equivalents and connections

    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
     Owen
    0.46
     Trotz
    0.46
     INCREASE
    0.45
     Greeks
    0.44
    ^{+
    0.44
     Little
    0.42
     Sabre
    0.42
    確かに
    0.42
    少し
    0.41
     Champions
    0.41
    POSITIVE LOGITS
    este
    0.45
    бан
    0.44
    DataType
    0.44
    łada
    0.43
    idade
    0.42
     tulee
    0.42
    锻
    0.42
    负担
    0.41
    lux
    0.41
    лица
    0.40
    Activations Density 0.010%

    No Known Activations