© 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. 68844
    Prev
    Next
    INDEX
    Explanations

    introduces broadcasts or chapters

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

    host introductions and greetings

    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
     mengatakan
    0.53
    reporter
    0.47
    說
    0.46
     säger
    0.44
    说明
    0.44
    说
    0.44
     berkata
    0.43
    電力
    0.43
     પાસે
    0.43
    今日の
    0.43
    POSITIVE LOGITS
     weakly
    0.50
     begin
    0.44
     arise
    0.44
     commences
    0.44
     commence
    0.44
     align
    0.43
     "
    0.42
     β
    0.41
     clears
    0.41
     begins
    0.41
    Activations Density 0.004%

    No Known Activations