© 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. 240307
    Prev
    Next
    INDEX
    Explanations

    bird seed and water

    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
     و
    0.54
     và
    0.53
     calves
    0.48
     رأس
    0.48
     and
    0.47
     calf
    0.47
     biliary
    0.46
    และ
    0.44
     كم
    0.43
     foc
    0.41
    POSITIVE LOGITS
     Counts
    0.48
     Narendra
    0.44
    🦉
    0.42
     Florida
    0.41
    )^{-
    0.40
     Rahul
    0.40
     Poison
    0.40
     மின்
    0.40
     Madden
    0.40
     Toxicity
    0.40
    Activations Density 0.010%

    No Known Activations