© 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. 37059
    Prev
    Next
    INDEX
    Explanations

    unusual tax

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

    image copying

    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
     sommige
    0.41
    ﾞ
    0.41
     Journey
    0.38
    .!
    0.38
     Impulse
    0.38
     때문
    0.38
    andled
    0.38
     செயல்
    0.37
    可持续
    0.37
    ٠
    0.37
    POSITIVE LOGITS
    𒉺
    0.47
    ARIOS
    0.46
    ETIC
    0.45
     सम्राट
    0.43
    ULS
    0.42
    𝒄
    0.42
     posteriorly
    0.42
    OGLE
    0.42
    राल
    0.41
    castellan
    0.41
    Activations Density 0.002%

    No Known Activations