© 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. 145333
    Prev
    Next
    INDEX
    Explanations

    numbers and specific contexts like 'days' or 'urgency'

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

    APIs, devices, revisit, price

    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
     கிடைத்த
    0.50
    Ski
    0.47
    u
    0.47
    লা
    0.46
    在這裡
    0.46
    os
    0.46
    odus
    0.46
    ো
    0.45
    مد
    0.45
    說
    0.45
    POSITIVE LOGITS
     kawa
    0.49
     sepol
    0.49
    校验
    0.49
    OLYBD
    0.46
     QUAL
    0.45
     scheda
    0.45
     BED
    0.44
     thorny
    0.44
    忘记
    0.44
     kya
    0.44
    Activations Density 0.001%

    No Known Activations