© 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. 16334
    Prev
    Next
    INDEX
    Explanations

    words ending in -an or -om

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

    informal greetings and conversation

    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
    ents
    0.54
    ala
    0.53
    ine
    0.52
    ого
    0.52
    emo
    0.51
    ง
    0.50
    eta
    0.49
    ini
    0.48
    angers
    0.48
    reason
    0.48
    POSITIVE LOGITS
     duż
    0.49
     artı
    0.49
     lecithin
    0.48
     fumar
    0.48
    婿
    0.48
     propyl
    0.47
     iesp
    0.47
     svil
    0.47
     aktywn
    0.46
     tùy
    0.46
    Activations Density 0.000%

    No Known Activations