© 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-65K
    7. 64092
    Prev
    Next
    INDEX
    Explanations

    objectives, questions, and data points

    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
    ना
    0.55
    ab
    0.54
     escritor
    0.46
    Có
    0.46
    لی
    0.45
    سی
    0.45
    u
    0.45
    نی
    0.44
    ब
    0.44
    i
    0.44
    POSITIVE LOGITS
     devoid
    0.49
    gewood
    0.48
    ickt
    0.47
     問
    0.46
    ρίας
    0.46
    populated
    0.46
    模样
    0.45
    fds
    0.45
     ظل
    0.44
     consistent
    0.44
    Activations Density 0.014%

    No Known Activations