© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 204726
    Prev
    Next
    INDEX
    Explanations

    submissive man, dress, virgin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     basadas
    0.58
     dificultades
    0.55
     puriso
    0.55
     expectativas
    0.52
     Caedwalla
    0.52
     ajj
    0.52
     сист
    0.51
    <unused1752>
    0.51
     hosp
    0.51
     tratar
    0.51
    POSITIVE LOGITS
    i
    0.55
    im
    0.54
    :
    0.54
    em
    0.52
    URL
    0.49
    om
    0.48
     URL
    0.48
    (
    0.45
    UN
    0.45
    et
    0.44
    Activations Density 0.003%

    No Known Activations