© 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. 165000
    Prev
    Next
    INDEX
    Explanations

    foreign words and phrases

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

    verbs linked to context

    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
    е
    0.56
    x
    0.53
    ang
    0.50
    icuous
    0.49
    기의
    0.49
    esi
    0.49
    cd
    0.48
    дио
    0.47
    f
    0.47
    angled
    0.46
    POSITIVE LOGITS
     oltre
    0.49
     terrest
    0.48
     myocytes
    0.47
     uży
    0.46
     použit
    0.46
     walkways
    0.46
     PZ
    0.45
     microphones
    0.45
     استخدم
    0.45
     permeability
    0.45
    Activations Density 0.001%

    No Known Activations