© 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. 113443
    Prev
    Next
    INDEX
    Explanations

    customer choice

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

    business and finance jargon

    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
    Zeit
    0.47
     seinen
    0.44
    üy
    0.43
    Bullet
    0.43
     .
    0.43
    ủa
    0.43
    house
    0.42
     Ruhe
    0.42
    Suburb
    0.42
    ський
    0.42
    POSITIVE LOGITS
     stratég
    0.52
    གས་
    0.52
    வனுக்கு
    0.48
    酈
    0.46
    ดี๋ยว
    0.45
     अवगत
    0.45
     जरूरतों
    0.45
    मिताभ
    0.44
    詡
    0.44
     hostages
    0.44
    Activations Density 0.000%

    No Known Activations