© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 199510
    Prev
    Next
    INDEX
    Explanations

    Bielefeld Chef Person J

    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_262k_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
    ),
    0.46
    us
    0.46
    ;
    0.43
    ären
    0.42
    ush
    0.42
    .,
    0.41
    d
    0.41
    itech
    0.40
    lin
    0.40
     endeavours
    0.40
    POSITIVE LOGITS
    つける
    0.50
    YOU
    0.48
    Vaterpolo
    0.47
    ggel
    0.45
    原始
    0.44
    ಘ
    0.44
    Პ
    0.43
    حات
    0.43
    fifty
    0.43
    Ἥ
    0.42
    Activations Density 0.015%

    No Known Activations