© 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. 136496
    Prev
    Next
    INDEX
    Explanations

    notes, copy, add

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

    core ideas, examples, VAT, evolutionary, investment

    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
    yyyy
    0.46
     COT
    0.46
     tím
    0.44
     karoti
    0.44
     vitth
    0.43
     peat
    0.43
     electrol
    0.42
    ु
    0.42
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.42
     aulas
    0.41
    POSITIVE LOGITS
     Plow
    0.47
     Віль
    0.46
     Health
    0.44
     홀
    0.44
     Operational
    0.44
     외부
    0.43
    lässlich
    0.43
    adores
    0.42
    探
    0.42
     이날
    0.41
    Activations Density 0.000%

    No Known Activations