© 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. 162973
    Prev
    Next
    INDEX
    Explanations

    we would recommend

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

    comparing models

    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
    3
    0.58
     weeks
    0.52
    ols
    0.49
    4
    0.49
    !
    0.47
    8
    0.46
    ence
    0.46
    lymp
    0.45
     Гон
    0.45
    BUST
    0.44
    POSITIVE LOGITS
    achery
    0.52
     කර
    0.44
    ร่
    0.42
    akura
    0.42
     luxuri
    0.42
    䇞
    0.41
     serre
    0.41
    矗
    0.41
    剡
    0.41
    ابہ
    0.41
    Activations Density 0.001%

    No Known Activations