© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 91527
    Prev
    Next
    INDEX
    Explanations

    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-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
     reflects
    0.45
    ɒ
    0.45
    ciudad
    0.44
     resides
    0.43
    нда
    0.43
     culminates
    0.43
    wohn
    0.43
     Uc
    0.42
     cuart
    0.42
     appealed
    0.41
    POSITIVE LOGITS
    姆
    0.44
    绵
    0.43
    טל
    0.42
    娄
    0.41
    头发
    0.40
    受伤
    0.39
    টন
    0.39
     scrapping
    0.39
    绦
    0.39
    천
    0.39
    Activations Density 0.009%

    No Known Activations