© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 9883
    Prev
    Next
    INDEX
    Explanations

    initially, though, first

    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_40_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
    ation
    0.32
    /
    0.32
     Le
    0.29
     зокрема
    0.28
    _
    0.26
    eroy
    0.25
    aka
    0.25
     magnification
    0.25
     division
    0.25
     Ridg
    0.25
    POSITIVE LOGITS
     क्योंकि
    0.34
     deportivos
    0.32
    тить
    0.32
    due
    0.31
    䉍
    0.30
     habría
    0.30
    StoredKeys
    0.30
     fomentar
    0.30
     politie
    0.30
    㸽
    0.30
    Activations Density 0.010%

    No Known Activations