© 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. 65311
    Prev
    Next
    INDEX
    Explanations

    joining specific words

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

    No Tools/Real-time Information

    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
    ጆች
    0.47
    ложений
    0.43
    essel
    0.43
    のための
    0.43
    вин
    0.42
    著名的
    0.41
     /
    0.41
     =
    0.41
     जब
    0.41
     通
    0.41
    POSITIVE LOGITS
     ক্ষয়
    0.45
     دوبارہ
    0.45
    excludes
    0.44
    Vamos
    0.43
     министер
    0.43
    Biggest
    0.42
     excludes
    0.42
     fanbase
    0.42
     Hades
    0.42
    শ্যাল
    0.42
    Activations Density 0.000%

    No Known Activations