© 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. 212597
    Prev
    Next
    INDEX
    Explanations

    selling orlead capture

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

    handling questions, reuse code, mounted file systems, limited parallelism

    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
    괴
    0.48
     armies
    0.47
    عية
    0.44
     verão
    0.42
    ایط
    0.41
     армии
    0.41
    垍
    0.41
    買い物
    0.41
     oraș
    0.40
    Укра
    0.39
    POSITIVE LOGITS
     gypsum
    0.54
     MAPE
    0.50
     PAD
    0.47
     PDP
    0.47
    e
    0.46
     XRD
    0.45
    y
    0.45
     Decree
    0.44
     SDA
    0.44
    i
    0.44
    Activations Density 0.001%

    No Known Activations