© 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. 163034
    Prev
    Next
    INDEX
    Explanations

    service department, thermal protection, packaged goods

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

    positive terminals, visualization libraries, branding

    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
    诽
    0.57
     ત્યારબાદ
    0.56
     부정
    0.54
     اداکار
    0.52
     Secretario
    0.51
    ivanje
    0.50
    窅
    0.49
    ugía
    0.49
     یا
    0.48
     Güzel
    0.48
    POSITIVE LOGITS
    6
    0.70
     enthusiasts
    0.68
     nationwide
    0.68
     emissions
    0.67
     powertrain
    0.67
     worldwide
    0.67
     fuels
    0.67
    ENERGY
    0.66
    4
    0.66
     megawatts
    0.65
    Activations Density 0.001%

    No Known Activations