© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 131387
    Prev
    Next
    INDEX
    Explanations

    linking words or phrases

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

    programming and examples

    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
    上の
    0.50
    О
    0.49
     निकाय
    0.49
     داخلی
    0.48
     tarixi
    0.47
     સ્થ
    0.47
     tarihi
    0.46
    िंग
    0.45
     શરૂ
    0.45
     місто
    0.45
    POSITIVE LOGITS
    acheteur
    0.46
    ↵
    0.44
    umiem
    0.43
     fico
    0.42
    camiseta
    0.42
     swells
    0.41
     খ্যা
    0.41
     unbelievable
    0.40
    ultat
    0.40
     хвати
    0.40
    Activations Density 0.000%

    No Known Activations