© 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. 225863
    Prev
    Next
    INDEX
    Explanations

    next week, best describes

    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
     excised
    0.49
    a
    0.47
     resist
    0.43
    或者
    0.42
    rés
    0.42
     vowels
    0.42
     Toto
    0.41
     ZTE
    0.41
     I
    0.41
     XO
    0.41
    POSITIVE LOGITS
    ням
    0.53
    ﺱ
    0.52
    ্যান
    0.51
    !:
    0.51
     :#
    0.51
    (':')[
    0.49
     กรณี
    0.47
    яз
    0.47
    стный
    0.46
    йл
    0.46
    Activations Density 0.001%

    No Known Activations