© 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. 9596
    Prev
    Next
    INDEX
    Explanations

    describing what images show

    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
    utiliser
    0.51
    ható
    0.40
    琹
    0.39
     okaz
    0.39
    殳
    0.39
     будет
    0.38
    quetas
    0.38
    omez
    0.38
    🇫
    0.38
    കാ
    0.38
    POSITIVE LOGITS
     actuation
    0.44
     ——
    0.41
     ;{
    0.40
     prelimin
    0.39
     LOOP
    0.39
     looping
    0.39
     그러니까
    0.39
     ORD
    0.39
     titled
    0.38
     callback
    0.38
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.