© 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. 158882
    Prev
    Next
    INDEX
    Explanations

    effort and achievement

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

    military build-ups or troop deployments

    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
    Phones
    0.52
    White
    0.47
     konkrét
    0.45
    కు
    0.45
    Reference
    0.44
    1
    0.44
    Grat
    0.44
    Optional
    0.43
    िएट
    0.42
    king
    0.42
    POSITIVE LOGITS
     amassed
    0.50
    ⌛
    0.45
     accolades
    0.43
     éxitos
    0.42
     efforts
    0.41
    getahuan
    0.41
     노력
    0.41
     fervor
    0.40
     again
    0.40
     اکنون
    0.40
    Activations Density 0.001%

    No Known Activations