© 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. 13843
    Prev
    Next
    INDEX
    Explanations

    two contrasting items

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

    contrasting ideas

    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
    力和
    0.42
    Female
    0.37
    Mode
    0.36
    3
    0.35
    5
    0.34
    Season
    0.34
    েল
    0.33
    enzione
    0.33
    ประโยชน์
    0.32
    five
    0.32
    POSITIVE LOGITS
     hingegen
    0.54
     natomiast
    0.50
     dagegen
    0.48
     zaś
    0.46
    則是
    0.44
    ՝
    0.44
    则是
    0.43
     correspondingly
    0.41
    jenigen
    0.41
     waxay
    0.41
    Activations Density 0.142%

    No Known Activations