© 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. 126272
    Prev
    Next
    INDEX
    Explanations

    stage of percentage by intensity correct

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

    percentage change

    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
    잽
    0.53
    ير
    0.49
    မျ
    0.49
     proposé
    0.46
    空的
    0.46
    syllabus
    0.46
    MF
    0.45
    τό
    0.45
    Спо
    0.45
    رود
    0.44
    POSITIVE LOGITS
    `
    0.49
    ´
    0.48
    ahs
    0.48
     housing
    0.46
    +"
    0.46
    ariam
    0.46
     Birth
    0.46
     ધર
    0.45
    }%
    0.45
     DoD
    0.44
    Activations Density 0.000%

    No Known Activations