© 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. 174807
    Prev
    Next
    INDEX
    Explanations

    end of sentence describing actions

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

    routes

    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
    儅
    0.46
     прием
    0.45
     proveedor
    0.44
     interfaz
    0.42
    CurrentUser
    0.42
    FUENTE
    0.42
     retorno
    0.41
    릉
    0.41
    ilan
    0.41
    اده
    0.40
    POSITIVE LOGITS
    罚
    0.48
     поради
    0.44
    处罚
    0.43
    enarios
    0.42
     prostaglandins
    0.42
    劭
    0.42
     Тар
    0.41
     پوری
    0.41
     умови
    0.41
     나누
    0.41
    Activations Density 0.000%

    No Known Activations