© 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. 127646
    Prev
    Next
    INDEX
    Explanations

    numbers and descriptive words

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

    those areas, investment, learned, Financial, consequences

    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
     květ
    0.52
    နှင့်
    0.49
    🤎
    0.47
     ház
    0.44
    🤍
    0.44
     टिकट
    0.44
     ২০২৩
    0.44
    uju
    0.44
    omu
    0.44
     寝
    0.44
    POSITIVE LOGITS
    مث
    0.46
     constituents
    0.45
     hydrocarbons
    0.45
     Supplemental
    0.43
     Vote
    0.42
    ذب
    0.42
     exportation
    0.42
    جل
    0.42
     Legislative
    0.41
    ريس
    0.41
    Activations Density 0.000%

    No Known Activations