© 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. 33465
    Prev
    Next
    INDEX
    Explanations

    foreign language text

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

    election, dust, inactivity

    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
     palettes
    0.52
     pledges
    0.49
     plaques
    0.47
    🥧
    0.47
    样
    0.46
     yar
    0.46
    ドル
    0.46
     cómo
    0.46
     licenses
    0.46
     maids
    0.46
    POSITIVE LOGITS
    \"{
    0.53
    ringen
    0.48
    \",
    0.47
    敎
    0.44
    Histoire
    0.44
    䍩
    0.43
    udent
    0.43
    CENTER
    0.42
    Câu
    0.42
    Extension
    0.42
    Activations Density 0.000%

    No Known Activations