© 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. 234431
    Prev
    Next
    INDEX
    Explanations

    procedure is performed

    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
     రాజ్య
    0.48
     ವ
    0.48
     Гали
    0.47
     vén
    0.46
     Claudio
    0.46
    rooms
    0.46
    iris
    0.45
     Schumacher
    0.45
     Mahindra
    0.45
     Daimler
    0.45
    POSITIVE LOGITS
    elace
    0.51
    皘
    0.46
    ﴾
    0.45
    ڑا
    0.44
     *
    0.44
    Lear
    0.44
     info
    0.44
    Biografia
    0.43
    Secrets
    0.43
     Arguments
    0.43
    Activations Density 0.000%

    No Known Activations