© 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. 16-GEMMASCOPE-2-RES-262K
    7. 14946
    Prev
    Next
    INDEX
    Explanations

    rainfall amounts, seasonality, intensity

    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_16_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
    ی
    1.60
    بد
    1.27
    ка
    1.27
    arı
    1.12
    arıyla
    1.10
    いる
    1.09
    rası
    1.09
    𝗴
    1.08
    ς
    1.07
    ၷ
    1.07
    POSITIVE LOGITS
    is
    1.69
    as
    1.59
    il
    1.56
    ing
    1.45
    al
    1.39
    '
    1.36
    ir
    1.34
    og
    1.32
    in
    1.19
    it
    1.18
    Activations Density 0.003%

    No Known Activations