© 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. 4216
    Prev
    Next
    INDEX
    Explanations

    on behalf of Study Notes

    np_acts-logits-general · gemini-2.5-flash-lite

    section headings

    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
    য়
    0.44
     infrastructures
    0.43
    簾
    0.43
    Sang
    0.42
     ANY
    0.42
     Mapping
    0.41
     mapping
    0.41
    ಡಿಯ
    0.41
     аккумуля
    0.40
    D
    0.40
    POSITIVE LOGITS
    oje
    0.56
     물질
    0.49
    ์
    0.48
    attoo
    0.47
     صلی
    0.47
     pancreatitis
    0.46
     summarizes
    0.46
     summarizing
    0.46
     grie
    0.46
     denoted
    0.46
    Activations Density 0.000%

    No Known Activations