© 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. 74037
    Prev
    Next
    INDEX
    Explanations

    rubber, latex, TPU

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

    rubber and latex

    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
    羢
    0.48
    📡
    0.46
    কাত
    0.46
    ITwitter
    0.46
     মির
    0.45
    ⣶
    0.45
     красиво
    0.45
     гене
    0.44
    眈
    0.44
    ಂತರ
    0.43
    POSITIVE LOGITS
     rubber
    1.34
     Rubber
    1.28
    Rubber
    1.28
    rubber
    1.27
     caoutchouc
    1.07
    橡胶
    1.07
     rubbers
    1.04
     elastomer
    1.03
     elastomers
    1.01
     latex
    0.91
    Activations Density 0.221%

    No Known Activations