© 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. 24267
    Prev
    Next
    INDEX
    Explanations

    risk

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

    gods themselves

    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
    طفال
    0.47
    ßerdem
    0.47
    堡
    0.47
     ได้
    0.46
    غو
    0.44
    <unused78>
    0.44
     Schä
    0.44
    ยังมี
    0.44
     Boe
    0.43
     ਹੋ
    0.42
    POSITIVE LOGITS
    rit
    0.51
    ENERGY
    0.50
    Liam
    0.48
    UST
    0.48
    simplified
    0.48
    from
    0.46
    Joel
    0.46
    á
    0.45
    EAR
    0.44
    𝐸
    0.44
    Activations Density 0.000%

    No Known Activations