© 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. 195070
    Prev
    Next
    INDEX
    Explanations

    antique, song, units, status, money

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

    list item starters

    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
    اں
    0.49
    ｧ
    0.47
     realização
    0.47
    䔉
    0.47
    아서
    0.46
    唓
    0.46
    ரம்
    0.45
    מוד
    0.45
    ்
    0.45
     avance
    0.44
    POSITIVE LOGITS
    嚼
    0.45
     oatmeal
    0.44
     Estrada
    0.40
    િજા
    0.39
    rtol
    0.38
     வழங்கப்படும்
    0.38
     дү
    0.38
    ™,
    0.37
     Chevrolet
    0.37
     Aircraft
    0.37
    Activations Density 0.000%

    No Known Activations