© 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. 196921
    Prev
    Next
    INDEX
    Explanations

    fore deck

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

    vertical, upward, moving, subtly

    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
     lighten
    0.52
     Walther
    0.52
    :
    0.47
     mun
    0.46
    ίδ
    0.46
     wzgl
    0.46
     LIGHT
    0.45
     tigris
    0.45
     later
    0.44
     lig
    0.44
    POSITIVE LOGITS
    mazing
    0.46
    tey
    0.46
    analisi
    0.46
    amazing
    0.45
    shar
    0.45
    tiene
    0.43
    膩
    0.43
     चैंपियनशिप
    0.43
     विश्लेषण
    0.42
    अपना
    0.41
    Activations Density 0.001%

    No Known Activations