© 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. 162137
    Prev
    Next
    INDEX
    Explanations

    season

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

    dates, months, or conditions

    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
     Dirk
    0.53
     Brigitte
    0.53
     Nick
    0.53
     Briggs
    0.52
     Bamberg
    0.51
     Tatha
    0.50
    ।*
    0.50
    )}$.
    0.50
     Schw
    0.49
     Owen
    0.49
    POSITIVE LOGITS
    ％
    0.47
    antenna
    0.44
    änd
    0.44
    
    0.43
    azole
    0.42
    ands
    0.42
    atures
    0.41
    play
    0.41
    อย่าง
    0.41
    C
    0.41
    Activations Density 0.000%

    No Known Activations