© 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. 40-GEMMASCOPE-2-RES-16K
    7. 10168
    Prev
    Next
    INDEX
    Explanations

    methods for or of

    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_40_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
    erre
    0.46
    et
    0.43
    쫀득
    0.42
    8
    0.41
    in
    0.41
    nH
    0.41
     funzione
    0.41
    맵
    0.40
    ൂട്ട
    0.40
    w
    0.40
    POSITIVE LOGITS
    ologically
    0.52
    ological
    0.50
    ologischen
    0.50
    OLOGICAL
    0.47
     없습니다
    0.46
    សា
    0.45
    ológico
    0.44
    quí
    0.44
    ically
    0.44
    ologisch
    0.44
    Activations Density 0.069%

    No Known Activations