© 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. 139460
    Prev
    Next
    INDEX
    Explanations

    time, currency, or location

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

    water and exist

    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
    жается
    0.51
     Assay
    0.48
    Contact
    0.45
    বের
    0.44
    izzes
    0.44
     points
    0.43
    ="
    0.43
    စေ
    0.43
    kowicz
    0.42
    rifice
    0.42
    POSITIVE LOGITS
    ুপ
    0.49
     bahwa
    0.49
     balon
    0.47
     kij
    0.47
     이용해서
    0.47
     지
    0.46
    CHREIB
    0.46
     kunci
    0.46
     linea
    0.45
     bahawa
    0.44
    Activations Density 0.000%

    No Known Activations