© 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. 20706
    Prev
    Next
    INDEX
    Explanations

    publication names followed by reports

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

    improving, reaching, gap, data, security, tasks, learned

    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
     recommendation
    0.45
    わ
    0.44
     chosen
    0.43
     one
    0.43
    recommend
    0.43
     unique
    0.42
    ：
    0.41
     स्वाभाविक
    0.41
     CHOICE
    0.41
    ↵↵
    0.40
    POSITIVE LOGITS
     نیست
    0.44
     বাড়ী
    0.41
     nebude
    0.39
    都不会
    0.38
    逾
    0.38
    नामी
    0.38
     ไม่มี
    0.37
    Zig
    0.37
    樾
    0.36
    ConfigSource
    0.36
    Activations Density 0.000%

    No Known Activations