© 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. 48631
    Prev
    Next
    INDEX
    Explanations

    rapidly ideate

    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
    im
    0.57
    n
    0.52
    x
    0.49
    es
    0.46
    it
    0.46
     $
    0.45
    is
    0.45
    in
    0.45
    u
    0.45
    en
    0.44
    POSITIVE LOGITS
    𒈪
    0.52
     niem
    0.50
    avacanam
    0.49
    akter
    0.48
    𒈬
    0.48
    BITMAP
    0.48
    <unused740>
    0.48
    InCM
    0.48
    嫄
    0.48
    ccncc
    0.47
    Activations Density 0.003%

    No Known Activations