© 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. 34104
    Prev
    Next
    INDEX
    Explanations

    of the current

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

    target function, predicted values

    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
    又要
    0.50
     weiteren
    0.44
     siguientes
    0.43
    귿
    0.43
     nuevamente
    0.42
     prochains
    0.42
    再次
    0.41
     additional
    0.41
    에
    0.41
    JL
    0.40
    POSITIVE LOGITS
    ammatory
    0.46
    στά
    0.45
     автоматы
    0.44
    throwing
    0.44
    汥
    0.42
    executor
    0.42
    visually
    0.42
    Diffusion
    0.42
    collected
    0.42
    ous
    0.40
    Activations Density 0.000%

    No Known Activations