© 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. 29225
    Prev
    Next
    INDEX
    Explanations

    sweeping out, never mind, I'm

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

    brew method

    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
    ாலி
    0.44
     lente
    0.44
     солнце
    0.44
     transference
    0.43
     assent
    0.42
     пуль
    0.42
     IGBT
    0.42
    铵
    0.42
     squ
    0.42
     quiescent
    0.42
    POSITIVE LOGITS
     tujuh
    0.52
     apoio
    0.50
     দেশের
    0.47
     trei
    0.47
    Eine
    0.47
     drei
    0.47
     Arrays
    0.47
     ovat
    0.46
     digelar
    0.46
     poems
    0.46
    Activations Density 0.000%

    No Known Activations