© 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. 6359
    Prev
    Next
    INDEX
    Explanations

    i will explain

    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
     calibr
    0.47
     vox
    0.44
     attenuation
    0.42
    calibrate
    0.41
    掖
    0.40
     granularity
    0.39
     calibrations
    0.39
     viscosity
    0.39
     calibrate
    0.39
     aquaculture
    0.38
    POSITIVE LOGITS
    of
    0.46
    そして
    0.44
    он
    0.43
    which
    0.43
    ↵↵
    0.42
    and
    0.42
    rdquo
    0.39
    और
    0.38
    р
    0.38
    accesso
    0.37
    Activations Density 0.187%

    No Known Activations