© 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. 40-GEMMASCOPE-2-RES-262K
    7. 167093
    Prev
    Next
    INDEX
    Explanations

    action sheets and python commands

    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_40_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
     molécule
    0.44
     немец
    0.43
     направление
    0.41
     AppMethodBeat
    0.40
     német
    0.40
     молеку
    0.39
    ।*
    0.39
    舫
    0.38
    <unused86>
    0.37
    ském
    0.37
    POSITIVE LOGITS
    bar
    0.54
     bar
    0.49
     Bar
    0.47
     handle
    0.46
    BAR
    0.43
     dep
    0.42
    Bar
    0.41
     BAR
    0.40
     enam
    0.40
     dial
    0.39
    Activations Density 0.001%

    No Known Activations