© 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. 70666
    Prev
    Next
    INDEX
    Explanations

    common requirements

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

    worth common news number sustainable

    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
    是从
    0.48
    тті
    0.46
    У
    0.45
     Націона
    0.45
    Те
    0.44
    Ба
    0.44
     („
    0.43
    ául
    0.43
    সি
    0.43
     -"
    0.42
    POSITIVE LOGITS
     dhad
    0.55
     حساب
    0.54
     usu
    0.51
     دوس
    0.50
     solusi
    0.49
     ingresos
    0.49
    晟
    0.48
     sue
    0.48
     پیسہ
    0.47
     sempre
    0.47
    Activations Density 0.002%

    No Known Activations