© 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. 24695
    Prev
    Next
    INDEX
    Explanations

    monster, strategically, cats, prematurely, Google

    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
    imam
    0.44
    너
    0.43
    穗
    0.42
    Charged
    0.41
    ා
    0.40
    WOOD
    0.40
    anggap
    0.40
    ка
    0.40
    σε
    0.40
    Net
    0.39
    POSITIVE LOGITS
     y
    0.49
     contraste
    0.49
     gest
    0.47
     sliced
    0.46
     abertura
    0.43
     ri
    0.43
     slicing
    0.43
     h
    0.42
     rubbing
    0.42
     LIT
    0.42
    Activations Density 0.000%

    No Known Activations