© 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. 4045
    Prev
    Next
    INDEX
    Explanations

    state, objective, or entity

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

    problematic scenarios

    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
     Westport
    0.58
    ad
    0.54
                        
    0.53
    f
    0.53
    w
    0.52
     E
    0.50
    ana
    0.50
     $\
    0.49
     s
    0.49
     Operating
    0.49
    POSITIVE LOGITS
     தன்
    0.53
     riguardo
    0.52
     來
    0.50
    ӣ
    0.50
     rougeâtre
    0.48
     tendrán
    0.46
    雖
    0.46
    слей
    0.46
    ază
    0.46
     ראש
    0.46
    Activations Density 0.267%

    No Known Activations