© 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. 91527
    Prev
    Next
    INDEX
    Explanations

    provided disclaimers

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

    cautionary advice

    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
    ciudad
    0.48
     culminates
    0.47
    (
    0.46
     appealed
    0.45
     niên
    0.44
     شہر
    0.44
     город
    0.43
    ɒ
    0.43
     reflects
    0.43
     откро
    0.43
    POSITIVE LOGITS
    姆
    0.48
    绵
    0.48
    娄
    0.45
    טל
    0.44
    受伤
    0.44
    绦
    0.44
    천
    0.43
     HttpException
    0.42
    ベーション
    0.41
    폐
    0.41
    Activations Density 0.000%

    No Known Activations