© 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. 73568
    Prev
    Next
    INDEX
    Explanations

    explains purpose or reason

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

    is a definition

    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
    聸
    0.53
     réussi
    0.48
     sembl
    0.45
     anmelden
    0.43
     alguno
    0.43
     mindestens
    0.42
     preocupación
    0.42
    ၉
    0.41
    ประสบ
    0.40
     longtemps
    0.40
    POSITIVE LOGITS
     will
    0.50
     helps
    0.47
     ignored
    0.46
     automatically
    0.44
    用来
    0.43
     gets
    0.42
     replaces
    0.41
     serves
    0.40
     используется
    0.40
     assumes
    0.40
    Activations Density 0.028%

    No Known Activations