© 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. 200651
    Prev
    Next
    INDEX
    Explanations

    essays and societal groups

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

    data and medical terms

    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
     endow
    0.49
    5
    0.46
    bilder
    0.45
     enrich
    0.43
     trz
    0.43
    samp
    0.42
     originating
    0.42
     imb
    0.42
     strs
    0.42
     рус
    0.42
    POSITIVE LOGITS
     हमारा
    0.51
     הד
    0.48
     nuestra
    0.47
    শাহ
    0.46
     هی
    0.45
    양
    0.45
     우리의
    0.45
     Pediatric
    0.45
     שלנו
    0.44
    욜
    0.44
    Activations Density 0.000%

    No Known Activations