© 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. 75534
    Prev
    Next
    INDEX
    Explanations

    sections and explanations

    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
    um
    0.55
    *
    0.55
    ear
    0.52
    rip
    0.52
    t
    0.52
    om
    0.51
    ww
    0.50
    ss
    0.48
    re
    0.47
    p
    0.46
    POSITIVE LOGITS
     ofertas
    0.52
     oczywiście
    0.51
     ouvrir
    0.50
     ovviamente
    0.50
     classique
    0.49
     decirlo
    0.49
     obviamente
    0.48
     ofrecemos
    0.47
     postérieures
    0.47
     opciones
    0.47
    Activations Density 0.002%

    No Known Activations