© 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. 247870
    Prev
    Next
    INDEX
    Explanations

    places and services

    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
    ur
    0.55
    as
    0.54
     for
    0.54
                           
    0.51
    している
    0.51
    us
    0.50
                    
    0.49
    asley
    0.49
    ));
    0.48
    ش
    0.48
    POSITIVE LOGITS
     portata
    0.51
     faiblement
    0.49
    惩
    0.48
     شي
    0.48
    か
    0.47
     rétr
    0.47
    滅
    0.45
     talisman
    0.44
     miserably
    0.44
    贍
    0.44
    Activations Density 0.000%

    No Known Activations