© 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. 67501
    Prev
    Next
    INDEX
    Explanations

    specialties and professions

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

    descriptions of processes or definitions

    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
    0.49
     Remembering
    0.44
    瞳
    0.42
    Audi
    0.42
    ஔ
    0.40
    Engel
    0.40
    Engagement
    0.40
    专
    0.40
    Andrea
    0.39
    Brid
    0.39
    POSITIVE LOGITS
     alleges
    0.49
     organisations
    0.49
     Metallurgy
    0.48
     keltiradi
    0.46
     estimates
    0.46
     enforces
    0.46
     flog
    0.46
     provoquer
    0.45
     senyawa
    0.45
    猚
    0.45
    Activations Density 0.000%

    No Known Activations