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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 1445
    Prev
    Next
    INDEX
    Explanations

    little, less, least

    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
    ts
    0.40
    ໝ
    0.37
    iaan
    0.36
     P
    0.33
     oraz
    0.33
    ަމ
    0.33
     allows
    0.32
    eteer
    0.32
    ema
    0.31
    ్ఞ
    0.31
    POSITIVE LOGITS
     $(<
    0.54
     chance
    0.50
     likelihood
    0.49
     직접
    0.48
     fuss
    0.47
     comparatively
    0.47
     directly
    0.46
    直接
    0.45
     appreciably
    0.44
     فرص
    0.44
    Activations Density 0.027%

    No Known Activations