© 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. 9841
    Prev
    Next
    INDEX
    Explanations

    file attachments and related actions

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

    okay, i will

    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
    解码
    0.40
    ەیە
    0.38
     :-)
    0.38
    䔧
    0.38
     spie
    0.37
     Lynx
    0.37
     px
    0.37
    ذهب
    0.37
     نزد
    0.37
     Decoder
    0.36
    POSITIVE LOGITS
     disorders
    0.37
    function
    0.35
    ₺
    0.35
    வன
    0.34
     otvor
    0.34
    ຜະລິດຕະພັນ
    0.34
     অপ্রত্যাশিত
    0.34
     анато
    0.33
    谔
    0.33
    Partition
    0.33
    Activations Density 0.000%

    No Known Activations