© 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. 7522
    Prev
    Next
    INDEX
    Explanations

    actually after not

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

    Elara

    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
    ент
    0.51
     ophthal
    0.51
    ופ
    0.49
    르
    0.47
    룔
    0.47
    HLER
    0.47
    。\
    0.46
    WIS
    0.46
    槳
    0.46
    COND
    0.46
    POSITIVE LOGITS
     hehe
    0.63
     Actually
    0.59
     Nhưng
    0.58
     really
    0.54
     Somehow
    0.54
     Honestly
    0.54
     Saying
    0.53
     That
    0.53
     Vậy
    0.53
     Really
    0.52
    Activations Density 0.012%

    No Known Activations