© 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. 238844
    Prev
    Next
    INDEX
    Explanations

    nature ofembedded questionsdisposal of

    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
    仲
    0.46
     Ceylon
    0.45
    design
    0.45
    レイン
    0.43
     Survey
    0.41
    生命
    0.41
    fashion
    0.41
     Shield
    0.41
    Coffee
    0.41
     Coffee
    0.41
    POSITIVE LOGITS
     நேரடியாக
    0.52
     заход
    0.52
     offenen
    0.50
     baixar
    0.50
    ∖
    0.49
    ്ലാ
    0.49
     sederhana
    0.49
     duż
    0.49
     poziomie
    0.48
    послед
    0.47
    Activations Density 0.001%

    No Known Activations