© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 225711
    Prev
    Next
    INDEX
    Explanations

    instructions or suggestions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    καν
    0.45
     सम्बन्ध
    0.45
    处
    0.45
    赔
    0.45
     amarelo
    0.44
    теру
    0.42
     remedied
    0.41
     bullies
    0.41
     sebepler
    0.41
     bullied
    0.40
    POSITIVE LOGITS
    ^{+}$.
    0.38
    chro
    0.37
    wä
    0.37
    ędz
    0.37
    ürich
    0.37
    contour
    0.36
    getApplication
    0.36
     หลังจาก
    0.36
     التن
    0.36
    Robertson
    0.36
    Activations Density 0.001%

    No Known Activations