© 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. 156103
    Prev
    Next
    INDEX
    Explanations

    interim interim Blog

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

    cloud backend server container

    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
     refrigerators
    0.46
    還可以
    0.43
    ૃ
    0.43
     чрезвы
    0.43
     povos
    0.42
     всю
    0.41
     problèmes
    0.41
     chuột
    0.41
    ᱐
    0.40
     protons
    0.40
    POSITIVE LOGITS
     interim
    0.54
     nahm
    0.48
     Erick
    0.46
    Blog
    0.46
     Robyn
    0.45
     (
    0.45
     Elie
    0.44
     Blog
    0.44
     pach
    0.44
     Interim
    0.44
    Activations Density 0.002%

    No Known Activations