© 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. 126280
    Prev
    Next
    INDEX
    Explanations

    reports memory, negotiate peace, buy for, reduce plastic

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

    ending statements with questions

    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
     പ്രച
    0.56
    ?»
    0.52
     ረ
    0.50
     잠깐
    0.49
     জঙ্গি
    0.49
     મહિ
    0.48
     लगभग
    0.47
     అనేక
    0.47
     சரியான
    0.47
     비슷한
    0.46
    POSITIVE LOGITS
    <0x0D>
    0.54
     intrauterine
    0.51
    ihydro
    0.48
    xas
    0.47
     acides
    0.47
    1
    0.47
     of
    0.46
    my
    0.46
    komst
    0.44
     acide
    0.44
    Activations Density 0.000%

    No Known Activations