© 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. 36487
    Prev
    Next
    INDEX
    Explanations

    Color or lifetime

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

    excellent free

    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
     <?
    0.45
    Mockito
    0.43
    쐞
    0.41
     pretext
    0.41
    Config
    0.41
    STI
    0.41
    Paradise
    0.40
     server
    0.40
     version
    0.40
     COMMUNITY
    0.40
    POSITIVE LOGITS
     இள
    0.50
    y
    0.48
    swald
    0.47
     Alles
    0.47
     aconte
    0.46
    میں
    0.46
    кло
    0.44
     aange
    0.44
     číslo
    0.44
    воль
    0.44
    Activations Density 0.000%

    No Known Activations