© 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. 80440
    Prev
    Next
    INDEX
    Explanations

    business strategy

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

    origins and disclaimers

    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
    an
    0.64
    at
    0.59
    éget
    0.56
    im
    0.54
    att
    0.53
    ut
    0.53
    a
    0.52
    ih
    0.50
    ه
    0.50
    ik
    0.49
    POSITIVE LOGITS
     پیغمبر
    0.47
    ⊢
    0.44
     consacré
    0.43
     канцеля
    0.42
    PatientR
    0.42
    ভাষ
    0.42
     পর্যা
    0.42
    যুদ্ধ
    0.41
    Particle
    0.41
     سپورت
    0.41
    Activations Density 0.000%

    No Known Activations