© 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. 78283
    Prev
    Next
    INDEX
    Explanations

    my blog

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

    actions, generate, located, fulfill

    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
    0.56
    2
    0.56
    ES
    0.47
    3
    0.47
    a
    0.46
    P
    0.46
    雷
    0.45
      
    0.44
    extends
    0.44
    C
    0.43
    POSITIVE LOGITS
    ಾಂಶ
    0.59
     ડિ
    0.50
     ቀን
    0.50
     curtailed
    0.48
     sortir
    0.48
    lire
    0.47
    പ്പറ
    0.47
    ৪৭
    0.46
     አገልግሎ
    0.46
    locationY
    0.46
    Activations Density 0.000%

    No Known Activations