© 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. 161934
    Prev
    Next
    INDEX
    Explanations

    following punctuation

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

    excluding explicit or harmful content

    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
    에
    0.45
    ﺡ
    0.44
    stm
    0.42
     RAB
    0.41
    ﺃ
    0.41
     retrofit
    0.40
    늘
    0.40
    ﺁ
    0.40
     sequencer
    0.40
     Sandusky
    0.38
    POSITIVE LOGITS
    ະ
    0.50
     रचा
    0.50
    㶱
    0.49
     クリスマス
    0.49
    Мы
    0.48
    基本的に
    0.48
    様々な
    0.48
    学び
    0.47
    𝘳
    0.47
    Traditionally
    0.46
    Activations Density 0.004%

    No Known Activations