© 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. 236739
    Prev
    Next
    INDEX
    Explanations

    minimize disruptions

    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
     Vigil
    0.49
    晞
    0.48
     Beweg
    0.46
     Knife
    0.45
    篑
    0.45
    濑
    0.45
     Stre
    0.44
     Spro
    0.44
    Knife
    0.42
     entr
    0.42
    POSITIVE LOGITS
    ández
    0.49
    mlx
    0.47
    દર્શન
    0.47
    バー
    0.46
    img
    0.45
    ステップ
    0.44
    VALID
    0.43
    ;#
    0.43
    Imagem
    0.42
    nlp
    0.42
    Activations Density 0.001%

    No Known Activations