© 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. 233600
    Prev
    Next
    INDEX
    Explanations

    person/organization names

    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
     Consumers
    0.46
     INFORMATION
    0.46
     At
    0.45
     ABOUT
    0.44
     About
    0.43
     स्टेप
    0.43
     I
    0.43
     ".")
    0.42
     LITERATURE
    0.42
     indicator
    0.41
    POSITIVE LOGITS
    بح
    0.57
    琛
    0.54
    وبا
    0.52
    نان
    0.50
     നിന്നും
    0.50
    coeffs
    0.50
    inib
    0.50
    甠
    0.50
    нить
    0.50
    tcpHeader
    0.49
    Activations Density 0.000%

    No Known Activations