© 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. 47862
    Prev
    Next
    INDEX
    Explanations

    goat's milk

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

    a word followed by a descriptive noun

    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
    瑢
    0.51
    埝
    0.48
    产品
    0.47
    산
    0.47
    ദ്ധതി
    0.46
    璘
    0.45
    קת
    0.44
    牧
    0.44
    运动员
    0.43
    셀
    0.43
    POSITIVE LOGITS
    boarding
    0.52
     alcan
    0.52
    significant
    0.51
    indicated
    0.50
    lawful
    0.50
    state
    0.50
     cyclical
    0.50
    prefix
    0.50
    consistency
    0.50
    reliant
    0.50
    Activations Density 0.001%

    No Known Activations