© 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. 117645
    Prev
    Next
    INDEX
    Explanations

    leading to specific descriptions

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

    I've massive text

    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
    ൪
    0.51
    が増
    0.49
    𝕕
    0.47
    奈川
    0.47
    ონი
    0.47
     xī
    0.46
    ぢ
    0.45
    你有
    0.45
    俱
    0.45
    ድረ
    0.44
    POSITIVE LOGITS
     CURL
    0.55
     Prime
    0.46
     आणखी
    0.45
     is
    0.45
     C
    0.45
     folic
    0.45
     stereotype
    0.44
     Count
    0.44
     THR
    0.44
     epithelium
    0.44
    Activations Density 0.001%

    No Known Activations