© 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. 211441
    Prev
    Next
    INDEX
    Explanations

    no privacy, no shoving, no hysteria

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

    identifying specific information from tasks

    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
    ↵
    0.54
    kom
    0.53
    er
    0.51
     jasno
    0.51
    ella
    0.50
     składa
    0.49
    ie
    0.47
    am
    0.46
     dos
    0.46
    jas
    0.46
    POSITIVE LOGITS
    途径
    0.55
    口腔
    0.53
    鲢
    0.50
    变换
    0.50
    烀
    0.49
    腃
    0.48
    教室
    0.47
    崠
    0.47
    后者
    0.47
    инг
    0.46
    Activations Density 0.000%

    No Known Activations