© 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. 40-GEMMASCOPE-2-RES-262K
    7. 192491
    Prev
    Next
    INDEX
    Explanations

    neural networks talking about asking if born wild

    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_40_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
     goalie
    0.49
     goalt
    0.46
    Hockey
    0.44
    ockey
    0.41
     rink
    0.40
     tendance
    0.39
    🏒
    0.39
    雪
    0.39
     Skating
    0.38
     सम्मान
    0.38
    POSITIVE LOGITS
     ქვ
    0.41
     Lazar
    0.40
    \{-\
    0.39
    okol
    0.38
    FURNIZOR
    0.38
     Mediterr
    0.38
    ᅨ
    0.37
    Mediterr
    0.36
     Mediterranean
    0.36
    linebreak
    0.36
    Activations Density 0.001%

    No Known Activations