© 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. 200935
    Prev
    Next
    INDEX
    Explanations

    functional keywords

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

    explaining relationships and functions

    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
     breathless
    0.48
    𝒖
    0.46
     frantic
    0.43
     sophisticated
    0.42
    ա
    0.42
    を入力
    0.42
     frantically
    0.42
     した
    0.42
    ابی
    0.41
    を入れて
    0.41
    POSITIVE LOGITS
    l
    0.44
     amare
    0.43
    physics
    0.43
    function
    0.42
    tint
    0.42
    speaker
    0.41
    Growing
    0.41
    kry
    0.41
    Function
    0.41
    sees
    0.41
    Activations Density 0.001%

    No Known Activations