© 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. 67360
    Prev
    Next
    INDEX
    Explanations

    quantities and numbers

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

    lyrics and numbers

    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
     cpf
    0.51
     විසින්
    0.50
     arxiv
    0.46
    𝓛
    0.45
    𝒔
    0.44
    泻
    0.44
     estudo
    0.44
    ்கு
    0.44
    ዎ
    0.43
     હત
    0.43
    POSITIVE LOGITS
    ayscale
    0.49
     تعداد
    0.48
     NUMBER
    0.46
    歌詞
    0.46
    เลข
    0.43
     jumlah
    0.42
    array
    0.41
     সংখ্যা
    0.41
    authentic
    0.41
    歌曲
    0.40
    Activations Density 0.002%

    No Known Activations