© 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. 115781
    Prev
    Next
    INDEX
    Explanations

    Individual Portfolio

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

    house, cottage, lighthouse

    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
    ૭
    0.57
    يري
    0.55
    阍
    0.54
    䁂
    0.50
    vaise
    0.49
    öglichkeiten
    0.49
    醺
    0.49
     économiques
    0.49
    كة
    0.48
     combatt
    0.48
    POSITIVE LOGITS
    swith
    0.49
    かけて
    0.48
     '-
    0.44
    painting
    0.44
    YAN
    0.43
     deliver
    0.42
     menyimpan
    0.42
     nyata
    0.42
     mengingat
    0.41
    swing
    0.41
    Activations Density 0.001%

    No Known Activations