© 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. 243536
    Prev
    Next
    INDEX
    Explanations

    functional words followed by specific continuations

    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
    鈔
    0.44
     नौकरी
    0.44
    瘧
    0.42
    灘
    0.41
     অঙ্
    0.41
    攻
    0.41
    arit
    0.40
    他就
    0.40
    cmath
    0.40
    魚
    0.39
    POSITIVE LOGITS
     préférable
    0.52
     effectual
    0.49
     względu
    0.47
    分为
    0.45
     Czę
    0.44
    üsse
    0.44
    ிலோ
    0.44
     circumstance
    0.44
     Gött
    0.44
     Eğer
    0.44
    Activations Density 0.003%

    No Known Activations