© 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. 23202
    Prev
    Next
    INDEX
    Explanations

    buried at, have free

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

    words ending in `ed` followed by `in`

    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
    廿
    0.49
    ер
    0.48
    ут
    0.48
     sostit
    0.48
    фо
    0.48
    пель
    0.47
    quin
    0.46
     quale
    0.46
    ливо
    0.46
    idoscope
    0.46
    POSITIVE LOGITS
    t
    0.50
     প্রকৃত
    0.49
     نز
    0.49
     آزم
    0.48
    ت
    0.48
     एक्सप्ले
    0.46
     যারা
    0.45
     Candidates
    0.45
    subset
    0.45
     enumeration
    0.44
    Activations Density 0.000%

    No Known Activations