© 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. 234862
    Prev
    Next
    INDEX
    Explanations

    potential clients

    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
    hits
    0.48
    (
    0.44
    li
    0.43
    rede
    0.42
    shmi
    0.41
    –
    0.41
     multiplets
    0.41
    [
    0.41
       
    0.40
    queries
    0.40
    POSITIVE LOGITS
     Хар
    0.59
     Abschnitt
    0.54
     اعتق
    0.54
     tentu
    0.52
     magasiner
    0.51
    чных
    0.50
    اردوش
    0.50
     Giveen
    0.50
    อาจ
    0.50
     Сте
    0.49
    Activations Density 0.001%

    No Known Activations