© 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. 107522
    Prev
    Next
    INDEX
    Explanations

    dosage or speeds

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

    companies, places, and programming constructs

    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
    system
    0.50
    աստ
    0.46
    VIEWS
    0.46
    𝐫
    0.46
    TURN
    0.45
    COUNTER
    0.45
    Ꮄ
    0.45
    ア
    0.45
    DARK
    0.44
    システム
    0.44
    POSITIVE LOGITS
     PwC
    0.50
     French
    0.48
     frances
    0.48
     Luffy
    0.47
     Presidente
    0.47
     Qxb
    0.46
     LinkedIn
    0.46
     Mourinho
    0.46
     Leandro
    0.45
     Sarah
    0.44
    Activations Density 0.000%

    No Known Activations