© 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. 76316
    Prev
    Next
    INDEX
    Explanations

    common phrases and collocations

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

    words related to actions and states

    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
     Crus
    0.46
    šli
    0.46
     но
    0.45
     dissoci
    0.45
     webs
    0.44
     Ξ
    0.44
    izaje
    0.44
    ‐
    0.43
    ლება
    0.43
     ISIS
    0.43
    POSITIVE LOGITS
    ผม
    0.47
    給我
    0.45
    زد
    0.44
    DON
    0.44
    }
    0.43
    าท
    0.42
     herein
    0.41
    吸收
    0.41
    風格
    0.41
    OV
    0.41
    Activations Density 0.000%

    No Known Activations