© 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. 128089
    Prev
    Next
    INDEX
    Explanations

    what was once

    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
     ಹೆಸರು
    0.56
    转
    0.55
    Д
    0.51
    長い
    0.50
     проблемы
    0.50
    الح
    0.50
     பெயர்
    0.50
    Ft
    0.50
    만원
    0.49
    Teste
    0.49
    POSITIVE LOGITS
     picnics
    0.43
     playoffs
    0.42
    ；
    0.42
     picnic
    0.42
     crates
    0.41
     ci
    0.41
     reporters
    0.40
    :
    0.40
     amantes
    0.40
     crockery
    0.40
    Activations Density 0.004%

    No Known Activations