© 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. 251748
    Prev
    Next
    INDEX
    Explanations

    project and

    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
     yüzy
    0.53
    𝚖
    0.53
    甙
    0.47
    榻
    0.47
     ছত্র
    0.47
    éfonos
    0.47
     Kritik
    0.46
     yath
    0.46
    slüman
    0.46
     BSData
    0.45
    POSITIVE LOGITS
     location
    0.55
     $
    0.52
     someone
    0.51
    4
    0.51
     rural
    0.50
    ↵
    0.48
    location
    0.48
     photo
    0.48
     video
    0.48
     movie
    0.48
    Activations Density 0.000%

    No Known Activations