© 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. 194216
    Prev
    Next
    INDEX
    Explanations

    engage my audience

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

    examples, memories, children, time

    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
    is
    0.64
    K
    0.52
    З
    0.48
    address
    0.48
    url
    0.47
    hi
    0.47
    IS
    0.46
    IN
    0.46
    ="#
    0.46
    к
    0.46
    POSITIVE LOGITS
     যাহার
    0.52
    𝔬
    0.51
    avkhat
    0.50
     LOCCTR
    0.50
     tenacity
    0.50
     densément
    0.48
     doigts
    0.48
     괜
    0.47
     পাইয়া
    0.47
     сложности
    0.47
    Activations Density 0.000%

    No Known Activations