© 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. 89627
    Prev
    Next
    INDEX
    Explanations

    Build Bridges Not Walls Shirt

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

    university, available, history

    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
    ود
    0.43
    FieldContext
    0.41
     وحتى
    0.41
    ſon
    0.40
    居住
    0.40
    рё
    0.40
    穸
    0.40
     السيد
    0.40
    糟糕
    0.40
     तकरीबन
    0.40
    POSITIVE LOGITS
    ol
    0.51
    :-
    0.45
    কর্মী
    0.44
    cur
    0.44
    elast
    0.43
     attach
    0.43
    create
    0.42
    alli
    0.42
     キ
    0.42
    creat
    0.42
    Activations Density 0.000%

    No Known Activations