© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 43791
    Prev
    Next
    INDEX
    Explanations

    American Psycho, residuals, start access

    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
    illère
    0.47
    TextImage
    0.43
    屁
    0.42
     Histoire
    0.41
    道理
    0.40
    地に
    0.40
    上に
    0.39
    黉
    0.39
    cityName
    0.39
    viso
    0.39
    POSITIVE LOGITS
     agus
    0.48
    एट
    0.45
     optimise
    0.43
     despert
    0.42
     intercambio
    0.42
     mejoras
    0.41
     licences
    0.41
     svih
    0.41
     proizvoda
    0.41
    칩
    0.41
    Activations Density 0.002%

    No Known Activations