© 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. 14277
    Prev
    Next
    INDEX
    Explanations

    leave or leaving

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

    leaving something behind

    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
     ।,
    0.53
    f
    0.50
    9
    0.50
    c
    0.49
     avere
    0.48
    losti
    0.48
     לאחר
    0.47
    ❖
    0.47
     উঠেছে
    0.46
     önem
    0.46
    POSITIVE LOGITS
     Leaving
    1.09
     leave
    1.06
     Leave
    1.03
     оставля
    1.03
     laissé
    1.01
     leaving
    1.00
    leaving
    0.96
     laissent
    0.95
    leave
    0.93
     deix
    0.92
    Activations Density 0.073%

    No Known Activations