© 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. 3451
    Prev
    Next
    INDEX
    Explanations

    numbers, dates, punctuation

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

    model response markers

    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
    क्यूमेंट
    0.29
    शिलाजीत
    0.28
    ড়যন্ত্র
    0.28
    त्रेयी
    0.28
    кмекер
    0.27
     ইলেক্ট্রোড
    0.27
    𒁀
    0.27
    लंघन
    0.27
    ণাস্ত্র
    0.27
    iffent
    0.26
    POSITIVE LOGITS
    ,
    0.45
    .
    0.37
    ↵↵
    0.37
    ↵
    0.36
     -
    0.36
    ;
    0.36
    :
    0.35
     I
    0.35
     The
    0.34
     and
    0.33
    Activations Density 0.084%

    No Known Activations