© 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. 2713
    Prev
    Next
    INDEX
    Explanations

    lists and tags

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

    phrases in lists

    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
     maintenir
    0.23
     abrang
    0.23
     nourrice
    0.23
     syphilit
    0.23
     pabb
    0.23
     nahe
    0.22
     ríg
    0.22
    ṱ
    0.22
     sujeito
    0.22
     potens
    0.22
    POSITIVE LOGITS
     G
    0.23
     R
    0.22
     जानिए
    0.22
     A
    0.22
     The
    0.21
     S
    0.21
     I
    0.20
     M
    0.20
    i
    0.20
     गौरतलब
    0.20
    Activations Density 0.429%

    No Known Activations