© 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. 164856
    Prev
    Next
    INDEX
    Explanations

    wreck whatsoever

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

    drawing lines and beads

    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
    ystycz
    0.48
     પારિજા
    0.46
    ي
    0.46
    𝐩
    0.46
    𝐭
    0.45
    eenth
    0.44
    SizeBytes
    0.43
    pective
    0.43
    benzoyl
    0.43
    cı
    0.42
    POSITIVE LOGITS
    नव
    0.52
     höheren
    0.45
     vector
    0.45
     calci
    0.45
    ].[
    0.44
     category
    0.43
     реакции
    0.43
     doc
    0.43
    稳
    0.43
    跟
    0.42
    Activations Density 0.000%

    No Known Activations