© 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. 131730
    Prev
    Next
    INDEX
    Explanations

    crossroads, intersection, legitimate

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

    providing information and speaking

    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
    ನ
    0.57
    ܘܢ
    0.49
    ATO
    0.49
    Evento
    0.49
     BusABC
    0.48
    ONY
    0.47
    MANAGER
    0.47
    Called
    0.47
    Geme
    0.47
    וני
    0.47
    POSITIVE LOGITS
    '
    0.47
    ils
    0.44
    ering
    0.42
     boots
    0.42
     laptop
    0.41
     Torres
    0.41
    ating
    0.40
     Tompkins
    0.40
    .
    0.40
     widening
    0.40
    Activations Density 0.001%

    No Known Activations