© 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. 32579
    Prev
    Next
    INDEX
    Explanations

    Mr. and titles

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

    style

    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
    delta
    0.41
    MODEL
    0.39
    raining
    0.38
    rho
    0.37
    DR
    0.36
    리
    0.36
    𝙉
    0.36
    olina
    0.36
    esini
    0.36
    MAF
    0.35
    POSITIVE LOGITS
    工商
    0.37
    сез
    0.37
    सर्
    0.36
    阏
    0.35
    袅
    0.35
    ལ
    0.35
    कान
    0.34
    Toc
    0.34
    unteer
    0.34
     तेरा
    0.34
    Activations Density 0.002%

    No Known Activations