© 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. 4408
    Prev
    Next
    INDEX
    Explanations

    compound noun phrases

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

    Power automate, Business plan

    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
    Azur
    0.17
     thi
    0.17
     southernmost
    0.17
     Batman
    0.17
     broadest
    0.17
     lakeside
    0.17
    ഓ
    0.17
     southern
    0.16
    的這個
    0.16
    nesday
    0.16
    POSITIVE LOGITS
    ங்கை
    0.21
     Decreto
    0.21
    申し込み
    0.20
    ática
    0.20
    ificazione
    0.20
     প্রক্রিয়া
    0.19
    Colonne
    0.19
    𝘬
    0.19
    睬
    0.19
     Etiquetas
    0.19
    Activations Density 0.394%

    No Known Activations