© 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. 248693
    Prev
    Next
    INDEX
    Explanations

    in publications and academic texts

    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
    '
    0.51
     imports
    0.51
    বাড়
    0.50
     bung
    0.50
     commands
    0.50
    কিন
    0.49
     paramedic
    0.49
     labels
    0.48
    Fridge
    0.48
     गरिएको
    0.47
    POSITIVE LOGITS
     தன்
    0.54
     قرار
    0.52
     نسبت
    0.51
     مانند
    0.48
     کن
    0.48
     합
    0.46
    ↖
    0.46
     මු
    0.45
     acuerdo
    0.45
     کنند
    0.44
    Activations Density 0.000%

    No Known Activations