© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 142272
    Prev
    Next
    INDEX
    Explanations

    Should I / What is

    np_acts-logits-general · gemini-2.5-flash-lite

    cats, European, Environment, commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tra
    0.43
    Tra
    0.42
    łu
    0.42
     সম্মানিত
    0.41
    mathfrak
    0.40
    长
    0.40
    omics
    0.40
    friends
    0.39
    宗旨
    0.39
    ম
    0.39
    POSITIVE LOGITS
     shouldn
    0.55
     Shouldn
    0.46
    пан
    0.45
     pogled
    0.43
    ្នក
    0.43
     Javed
    0.43
     `<=
    0.42
     muest
    0.41
    IGNORE
    0.41
     Should
    0.40
    Activations Density 0.000%

    No Known Activations