© 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. 180946
    Prev
    Next
    INDEX
    Explanations

    counting numbers

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

    Universal, Cultural, Different

    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
    дія
    0.50
    BuildConfig
    0.45
    Deque
    0.45
    栾
    0.45
    Verify
    0.44
    车辆
    0.44
    çe
    0.43
    گانی
    0.43
    Pune
    0.43
     в
    0.41
    POSITIVE LOGITS
    rats
    0.55
     sechs
    0.54
     semanal
    0.48
     rats
    0.47
     चित्रित
    0.47
     vier
    0.47
     six
    0.46
    atah
    0.46
     jedna
    0.45
     యుద్ధ
    0.45
    Activations Density 0.000%

    No Known Activations