© 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. 154092
    Prev
    Next
    INDEX
    Explanations

    Finest Hour

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

    APIs

    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
     twists
    0.50
     Jonathan
    0.47
     by
    0.46
    >')
    0.43
     grub
    0.42
     இறுதியில்
    0.42
     Jeffrey
    0.42
     Dominic
    0.41
    hagen
    0.40
     সড়ক
    0.39
    POSITIVE LOGITS
    的车
    0.50
    탕
    0.46
     اکثریت
    0.46
    üşt
    0.46
    ın
    0.46
     kleine
    0.45
    owanie
    0.45
    惪
    0.45
     கை
    0.44
    ować
    0.44
    Activations Density 0.001%

    No Known Activations