© 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. 227316
    Prev
    Next
    INDEX
    Explanations

    musical theatre

    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
    ah
    0.50
    aliy
    0.50
    ur
    0.49
    ੱਸ
    0.49
    elat
    0.48
    ="
    0.48
    alah
    0.48
    alen
    0.47
    el
    0.47
    anet
    0.47
    POSITIVE LOGITS
    せずに
    0.51
     samtid
    0.49
    িয়োগ
    0.49
     を
    0.47
    ﻒ
    0.47
    Kabhi
    0.46
    গারে
    0.46
     earring
    0.45
     simultaneously
    0.45
    ﺴ
    0.44
    Activations Density 0.000%

    No Known Activations