© 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. 13446
    Prev
    Next
    INDEX
    Explanations

    universities in, long-vacant

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

    parsing and analyzing information

    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
     bucks
    0.48
     you
    0.46
    pt
    0.45
     factor
    0.43
     unsure
    0.43
     ball
    0.42
     tariff
    0.42
    }_{\
    0.42
    ⁴
    0.42
     turb
    0.42
    POSITIVE LOGITS
    Geschichte
    0.57
    约翰
    0.52
     kendisine
    0.52
     እንዲሁም
    0.52
     Haziran
    0.51
     אס
    0.51
    க்கப்பட்ட
    0.51
    ศิลป
    0.50
    ıld
    0.49
    Legend
    0.49
    Activations Density 0.000%

    No Known Activations