© 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. 88215
    Prev
    Next
    INDEX
    Explanations

    legal and financial terms

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

    code file names and parameters

    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
    extrait
    0.57
    arrêté
    0.57
    phant
    0.54
    \{-
    0.53
    rafpunkte
    0.52
    orant
    0.52
    ense
    0.50
    enfant
    0.50
    ase
    0.49
    escal
    0.49
    POSITIVE LOGITS
     habría
    0.54
    真正的
    0.49
     ZH
    0.49
    ت
    0.47
    כ
    0.47
    ↵↵
    0.46
     reimburse
    0.46
     generously
    0.45
    0.44
     limestone
    0.43
    Activations Density 0.000%

    No Known Activations