© 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. 156458
    Prev
    Next
    INDEX
    Explanations

    Jerusalem third ASUS own market

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

    colors, responsibility, cell, industry, charts

    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
     emits
    0.49
     項
    0.48
     locationManager
    0.48
     tokamaks
    0.47
    (/^
    0.46
    ukaemia
    0.46
     tyres
    0.46
     রহিয়াছে
    0.46
    itio
    0.46
     cotton
    0.46
    POSITIVE LOGITS
    ه
    0.49
    h
    0.46
    ɢ
    0.45
    یل
    0.44
     literal
    0.44
    TEAM
    0.44
    హం
    0.43
     Exper
    0.42
     ciento
    0.42
    bowl
    0.41
    Activations Density 0.000%

    No Known Activations