© 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-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7617
    Prev
    Next
    INDEX
    Explanations

    I know, it is, prior

    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_16k_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
    人都
    0.41
     preocupación
    0.39
     uit
    0.37
    蓯
    0.37
     Chapter
    0.37
    }}-\
    0.37
     wollen
    0.37
     Austr
    0.36
    ysteine
    0.36
     vle
    0.36
    POSITIVE LOGITS
    Walls
    0.47
    Porsche
    0.44
    Puedes
    0.44
    ຯ
    0.44
    Came
    0.43
    Dogs
    0.43
    Voy
    0.43
    Muse
    0.43
    プス
    0.43
    Elekt
    0.42
    Activations Density 0.018%

    No Known Activations