© 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. 128291
    Prev
    Next
    INDEX
    Explanations

    garage flooring workshop floor

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

    fueled by, quickly than, remove the

    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
     トップ
    0.42
    巖
    0.42
     zien
    0.42
    ச
    0.42
    見
    0.42
    ハウス
    0.41
    スー
    0.41
    賀
    0.41
     பல்கலை
    0.41
    그룹
    0.41
    POSITIVE LOGITS
    delim
    0.46
    TextureAsset
    0.45
    
    0.44
     منط
    0.43
     अवि
    0.43
     "~/
    0.43
    composite
    0.42
     "/
    0.42
    舴
    0.42
     Preventing
    0.42
    Activations Density 0.001%

    No Known Activations