© 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. 194904
    Prev
    Next
    INDEX
    Explanations

    resident pastors

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

    evolving

    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
    appartement
    0.56
    德
    0.52
    音乐
    0.47
    epsilon
    0.46
    俄罗斯
    0.44
     长
    0.44
    治疗
    0.44
     kard
    0.43
     appartement
    0.43
     cominci
    0.43
    POSITIVE LOGITS
     gleaned
    0.50
     SSID
    0.45
    ਮ
    0.44
     COUNTY
    0.43
     valuations
    0.43
     LOCAL
    0.43
     embryonic
    0.42
     Secretariat
    0.42
    yscy
    0.42
     اقصیٰ
    0.41
    Activations Density 0.000%

    No Known Activations