© 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. 135704
    Prev
    Next
    INDEX
    Explanations

    is a

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

    yet, leakage, automate, read

    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
     حصل
    0.50
     obtient
    0.49
    ט
    0.49
     dadurch
    0.48
     dismin
    0.46
     sonucu
    0.44
    逐渐
    0.44
    <0xB2>
    0.43
    によっては
    0.43
    减轻
    0.43
    POSITIVE LOGITS
    ecology
    0.52
    wilderness
    0.51
    ipid
    0.49
     बी
    0.47
    termination
    0.47
    gies
    0.47
    state
    0.46
    donate
    0.46
    Need
    0.46
    Estado
    0.46
    Activations Density 0.000%

    No Known Activations