© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 13586
    Prev
    Next
    INDEX
    Explanations

    currency, numbers, or time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     +/-
    0.46
     digamos
    0.45
     XYZ
    0.41
     ________
    0.39
     _____________
    0.39
     Average
    0.38
     ____________
    0.37
     _____
    0.37
     ______
    0.37
     ic
    0.36
    POSITIVE LOGITS
    ópez
    0.36
    مدينة
    0.36
    لمين
    0.34
     pedagog
    0.33
     pedagogy
    0.33
     fondly
    0.32
     neque
    0.32
    ledovatel
    0.32
     apparently
    0.32
    ović
    0.32
    Activations Density 0.012%

    No Known Activations