© 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. 121211
    Prev
    Next
    INDEX
    Explanations

    Archived, Treaty, University, card, Release

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

    infotainment or multiculturalism

    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
    с
    0.49
    roff
    0.46
    ot
    0.46
    YE
    0.44
    シー
    0.44
    AR
    0.43
    ຽ
    0.42
    il
    0.42
     مادر
    0.41
    Sib
    0.41
    POSITIVE LOGITS
     বিষয়ে
    0.51
     treaties
    0.51
     infotainment
    0.48
     Treaty
    0.46
    खाने
    0.46
     Treatise
    0.45
     treaty
    0.45
     disrespectful
    0.45
    দেশের
    0.44
     Allies
    0.44
    Activations Density 0.001%

    No Known Activations