© 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. 31379
    Prev
    Next
    INDEX
    Explanations

    `import os`

    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
    Tangent
    0.44
     tactile
    0.42
    +
    0.41
     div
    0.41
     -
    0.40
    ~
    0.40
     otherwise
    0.39
    /
    0.39
     GUI
    0.39
     trapped
    0.39
    POSITIVE LOGITS
    íe
    0.51
    धियों
    0.51
    ഹ്ലാ
    0.50
    iej
    0.49
     teorías
    0.48
     اهل
    0.48
     آپ
    0.47
    iejs
    0.47
    ées
    0.47
    uksia
    0.46
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.