© 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. 246122
    Prev
    Next
    INDEX
    Explanations

    sequences ending with certain words

    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
    เยี่ยม
    0.47
     emailed
    0.45
     Recharge
    0.44
     `./
    0.44
     predmet
    0.43
    ņu
    0.43
     Бүгенге
    0.42
    明
    0.41
     Kün
    0.41
     deceduto
    0.41
    POSITIVE LOGITS
    Mathematics
    0.46
    it
    0.45
     significa
    0.44
    TED
    0.43
    OPS
    0.42
    Harm
    0.40
    tend
    0.40
    AppState
    0.40
     ಹಿಂದೆ
    0.40
    LAND
    0.39
    Activations Density 0.001%

    No Known Activations