© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 50118
    Prev
    Next
    INDEX
    Explanations

    code initialization

    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_65k_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
    T
    0.47
    filters
    0.46
     filtered
    0.45
     Finances
    0.45
    array
    0.44
    ura
    0.44
    writable
    0.43
    and
    0.43
    aid
    0.43
    functions
    0.43
    POSITIVE LOGITS
     =====
    0.49
     рэгістра
    0.48
     지
    0.48
    Mâc
    0.47
    🚺
    0.47
    IRCONIUM
    0.47
     personaggi
    0.46
    🔳
    0.46
    <0xA4>
    0.44
    лькі
    0.44
    Activations Density 0.002%

    No Known Activations