© 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. 127308
    Prev
    Next
    INDEX
    Explanations

    sealing meringue or every day

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

    Heritage science, materials, controlled drug release

    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
    вання
    0.52
     메소
    0.50
     된
    0.47
    вач
    0.47
    는
    0.46
    TypeOf
    0.46
     대한민국
    0.46
     المتوسط
    0.46
     결혼
    0.45
    NotFoundError
    0.44
    POSITIVE LOGITS
    SiO
    0.48
     Cm
    0.48
     COMMUNICATIONS
    0.47
     Y
    0.45
     Le
    0.45
     Cl
    0.44
     Captain
    0.44
     copying
    0.43
     SUBSTIT
    0.43
    鈴木
    0.43
    Activations Density 0.000%

    No Known Activations