© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 203132
    Prev
    Next
    INDEX
    Explanations

    list items and headings

    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
    Chim
    0.51
    veu
    0.49
    剑
    0.48
    Cairo
    0.47
    מ
    0.46
     سپورت
    0.46
    Arquivo
    0.46
     ಪಿ
    0.45
    Arvore
    0.44
    ן
    0.44
    POSITIVE LOGITS
     dollars
    0.51
     deficits
    0.48
     deadlines
    0.48
     bushels
    0.47
     allegiance
    0.46
     when
    0.45
     :/
    0.44
     underestimate
    0.44
     entities
    0.44
     dichotom
    0.43
    Activations Density 0.003%

    No Known Activations