© 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. 197252
    Prev
    Next
    INDEX
    Explanations

    punctuations and clauses

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

    energetic music and dramatic cuts

    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
     admiration
    0.50
    悗
    0.50
    อัต
    0.50
    评
    0.50
    的他
    0.47
     richiesta
    0.47
    讓他
    0.46
     atténuées
    0.46
    賢
    0.46
    恕
    0.46
    POSITIVE LOGITS
    Mes
    0.57
    El
    0.53
    Despite
    0.52
    receptor
    0.52
    1
    0.51
    despite
    0.49
    daughters
    0.49
    p
    0.49
     despite
    0.48
    o
    0.48
    Activations Density 0.001%

    No Known Activations