© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 195551
    Prev
    Next
    INDEX
    Explanations

    following conjunction

    np_acts-logits-general · gemini-2.5-flash-lite

    pure diamond

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gradation
    0.54
    ጷ
    0.46
    轫
    0.46
    加大
    0.45
    汇总
    0.45
    ના
    0.45
    ﮢ
    0.45
    눔
    0.44
    assurer
    0.43
    wärm
    0.43
    POSITIVE LOGITS
    I
    0.49
     I
    0.47
     ekonom
    0.46
    Pe
    0.44
     antics
    0.42
     vaults
    0.42
     telescopes
    0.42
    𝔰
    0.42
     nums
    0.41
     getType
    0.41
    Activations Density 0.000%

    No Known Activations