© 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. 92990
    Prev
    Next
    INDEX
    Explanations

    Taxi, film, Expansion, lungs, boys

    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
    cini
    0.48
    dą
    0.47
    bate
    0.46
    ontal
    0.45
    jar
    0.45
    c
    0.44
    减肥
    0.44
    财务
    0.44
    ים
    0.43
    caused
    0.43
    POSITIVE LOGITS
     Azad
    0.45
    Province
    0.44
     Mysore
    0.44
    残酷
    0.43
     निकाले
    0.43
     Gubernur
    0.43
    okan
    0.42
     locom
    0.42
     Resultado
    0.41
     मोहि
    0.41
    Activations Density 0.001%

    No Known Activations