© 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. 63192
    Prev
    Next
    INDEX
    Explanations

    hexadecimal strings or identifiers

    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
     Borders
    0.42
     Burgen
    0.42
     formulas
    0.41
     Conseils
    0.41
     Lesser
    0.41
     S
    0.40
     Sugar
    0.40
     Geografia
    0.40
     Medicinal
    0.40
     Daniels
    0.40
    POSITIVE LOGITS
    Why
    0.44
    Network
    0.41
    IN
    0.39
    LSTM
    0.38
    は約
    0.38
    浅
    0.37
    Mind
    0.37
    Its
    0.37
    Depth
    0.37
    ckpt
    0.37
    Activations Density 0.013%

    No Known Activations