© 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. 4614
    Prev
    Next
    INDEX
    Explanations

    2, 3, 1, 4, ✈

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

    numbers in crisis lines and ratings

    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
     appBar
    0.29
     اداکار
    0.29
     groupBox
    0.28
    gdock
    0.27
     imasmim
    0.27
    Კ
    0.26
     Untersuch
    0.26
     εφαρμο
    0.26
    jiwarl
    0.26
    AutoStabilise
    0.26
    POSITIVE LOGITS
    0
    0.33
    -
    0.33
    &
    0.30
    he
    0.27
    <0xE3>
    0.27
    ii
    0.26
    or
    0.26
    max
    0.26
    2
    0.26
    0.26
    Activations Density 0.503%

    No Known Activations