© 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. 249420
    Prev
    Next
    INDEX
    Explanations

    check print

    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
    ier
    0.49
    яў
    0.49
    న్‌
    0.48
    的确
    0.48
     Freitag
    0.48
    ėmis
    0.46
     Denton
    0.46
    ṟ
    0.46
    ž
    0.45
    𝜃
    0.44
    POSITIVE LOGITS
     healing
    0.54
     говорю
    0.49
     salvar
    0.49
     sufferings
    0.49
     putative
    0.48
    ।'
    0.48
     generated
    0.48
     calc
    0.48
     elution
    0.48
     ended
    0.47
    Activations Density 0.001%

    No Known Activations