© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 9077
    Prev
    Next
    INDEX
    Explanations

    humor about movies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bik
    0.49
    주
    0.48
     exit
    0.46
    Sha
    0.46
    run
    0.44
     लिखना
    0.44
     jasa
    0.42
    a
    0.42
    品牌
    0.42
     participa
    0.42
    POSITIVE LOGITS
     khuẩn
    0.46
    ټبال
    0.45
    рів
    0.45
    velte
    0.44
    টিভ
    0.43
    ﻲ
    0.43
    pless
    0.42
     ಆಹಾರ
    0.42
    aried
    0.42
    ivet
    0.42
    Activations Density 0.006%

    No Known Activations