© 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. 113253
    Prev
    Next
    INDEX
    Explanations

    the ladies

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

    said he lost his voice

    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
     T
    0.59
    s
    0.57
    y
    0.52
    uring
    0.49
    acy
    0.49
     US
    0.49
     pole
    0.49
    arg
    0.48
    omy
    0.48
    dens
    0.47
    POSITIVE LOGITS
     жүктөө
    0.54
    彭
    0.53
     básicamente
    0.52
     corrigir
    0.50
    檤
    0.50
    実
    0.49
    ᒎ
    0.49
    苯
    0.48
     リン
    0.47
     proteínas
    0.46
    Activations Density 0.001%

    No Known Activations