© 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. 57715
    Prev
    Next
    INDEX
    Explanations

    statesman synchronization there places

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

    must have a valid reason

    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
     a
    0.50
    r
    0.50
    ：
    0.50
    ![
    0.49
    set
    0.48
     ya
    0.47
    Š
    0.46
     emo
    0.46
    ##
    0.46
    E
    0.45
    POSITIVE LOGITS
    ાઇ
    0.52
     अच्छी
    0.46
     अच्छा
    0.46
     ឬ
    0.46
    церт
    0.45
     अर्
    0.45
    vious
    0.45
     రాష్ట్ర
    0.45
     कॉलेजों
    0.44
    ाइस
    0.44
    Activations Density 0.000%

    No Known Activations