© 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. 44552
    Prev
    Next
    INDEX
    Explanations

    periods of time and payment

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

    sister age questions

    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
     trụ
    0.43
    叒
    0.41
    凋
    0.41
     ấy
    0.40
     scoff
    0.39
     still
    0.39
    ười
    0.39
     antioxidant
    0.39
    rebbe
    0.39
    完美的
    0.39
    POSITIVE LOGITS
    FINE
    0.48
    얏
    0.46
    gina
    0.46
    става
    0.44
     caution
    0.43
    *********/
    0.43
    caution
    0.42
    sale
    0.41
    டைந்த
    0.41
    licking
    0.41
    Activations Density 0.000%

    No Known Activations