© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 25042
    Prev
    Next
    INDEX
    Explanations

    real vs fictional people

    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
    茲
    0.45
     hauptsächlich
    0.41
     converters
    0.41
     получать
    0.41
     capitalize
    0.40
     inverter
    0.40
     subnet
    0.40
     laver
    0.40
     maximize
    0.40
     difficulté
    0.40
    POSITIVE LOGITS
     może
    0.48
    历史
    0.44
     why
    0.43
    Destroy
    0.43
    द
    0.42
    चर
    0.41
    也许
    0.41
    为何
    0.41
    Statement
    0.40
     mengapa
    0.40
    Activations Density 0.000%

    No Known Activations