© 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. 194946
    Prev
    Next
    INDEX
    Explanations

    commercial and vacant properties

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

    introducing biases

    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
    輥
    0.48
    спонд
    0.47
    례
    0.45
    人生
    0.45
     cendré
    0.44
     jdbcTemplate
    0.44
     fillColorSpace
    0.44
    ޯ
    0.43
    geschichte
    0.43
    ನ್ನ
    0.43
    POSITIVE LOGITS
     Commercial
    0.48
     invito
    0.45
     commer
    0.44
     commercial
    0.44
     Comercial
    0.41
     NE
    0.41
    broad
    0.41
    Commercial
    0.40
     Glu
    0.40
    മായും
    0.40
    Activations Density 0.005%

    No Known Activations