© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 31663
    Prev
    Next
    INDEX
    Explanations

    Data, VR, model

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    တင်
    0.44
     NOTHING
    0.42
    欤
    0.40
    殯
    0.40
     organisatie
    0.39
     Trying
    0.39
    ：「
    0.38
     coordinación
    0.38
     stars
    0.38
     trying
    0.38
    POSITIVE LOGITS
    framework
    0.45
    a
    0.39
    Saharan
    0.38
    dpy
    0.38
     Zas
    0.37
     Lugo
    0.37
    MgCl
    0.37
    ~\
    0.37
    getType
    0.37
     Preferences
    0.37
    Activations Density 0.000%

    No Known Activations