© 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. 248431
    Prev
    Next
    INDEX
    Explanations

    represent thishedge designationsimulationMicromax

    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
     frère
    0.59
    𝔬
    0.56
    úsica
    0.55
     médioc
    0.52
    𝔱
    0.52
     liée
    0.51
    ÇA
    0.51
     três
    0.51
    nements
    0.50
    𝖺
    0.50
    POSITIVE LOGITS
    最低
    0.50
    Ray
    0.46
     Siberia
    0.45
    Ig
    0.44
     Ray
    0.44
    Russell
    0.44
     settler
    0.44
     штат
    0.43
    注意
    0.43
    lowest
    0.43
    Activations Density 0.000%

    No Known Activations