© 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. 47976
    Prev
    Next
    INDEX
    Explanations

    descriptive and technical terms

    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
    sschutz
    0.46
    防
    0.46
    rsi
    0.43
     防
    0.43
    接続
    0.43
    cludes
    0.42
    вал
    0.42
    )')
    0.41
    _{(
    0.41
    無視
    0.40
    POSITIVE LOGITS
     nello
    0.48
     necessidade
    0.46
     mantel
    0.44
     amore
    0.44
     nevoia
    0.44
     grew
    0.44
    اری
    0.42
     avrebbe
    0.42
     sobr
    0.42
     Amen
    0.41
    Activations Density 0.002%

    No Known Activations