© 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. 145194
    Prev
    Next
    INDEX
    Explanations

    status, satisfaction, conservative, customers

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

    purpose, enhancement, guideline, laws

    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
     خب
    0.47
     גי
    0.47
    א
    0.45
     Dal
    0.44
     -------
    0.44
     ידי
    0.44
     Farmer
    0.43
    子里
    0.43
     أكبر
    0.43
     విషయ
    0.43
    POSITIVE LOGITS
     zealous
    0.46
     strangled
    0.46
    Ặ
    0.45
    dataTable
    0.45
    conjug
    0.44
    postal
    0.43
     कैलेंडर
    0.43
     または
    0.42
    calculator
    0.42
    ╽
    0.42
    Activations Density 0.000%

    No Known Activations