© 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. 143244
    Prev
    Next
    INDEX
    Explanations

    git checks it

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

    potential dangers and individuals

    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
    Lambda
    0.45
    mêmes
    0.45
     中
    0.44
    érées
    0.41
    lossen
    0.41
    ლება
    0.40
    俶
    0.40
    GB
    0.39
    лана
    0.39
    avigation
    0.38
    POSITIVE LOGITS
    सन्
    0.47
     सीई
    0.46
     recomand
    0.46
     zle
    0.46
    markup
    0.45
    पल
    0.45
    अनुसूचित
    0.44
    वरिश
    0.44
     ihtiy
    0.44
     കാരണം
    0.43
    Activations Density 0.002%

    No Known Activations