© 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. 165663
    Prev
    Next
    INDEX
    Explanations

    package.json configuration and scripts

    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
    Doe
    0.45
    Đ
    0.44
    है
    0.43
    íte
    0.42
    ect
    0.42
    Only
    0.42
    zí
    0.41
    凹
    0.41
    In
    0.41
    Before
    0.40
    POSITIVE LOGITS
     către
    0.50
     homologous
    0.43
     padlock
    0.43
     interpolate
    0.43
    ントリー
    0.42
     ehrlich
    0.42
     builder
    0.42
     wages
    0.42
     encoders
    0.42
     ausgel
    0.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.