© 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. 9370
    Prev
    Next
    INDEX
    Explanations

    recognizes it

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

    reached

    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
     powerAll
    0.42
     automático
    0.39
     terceiro
    0.39
    畬
    0.39
     همین
    0.38
     kinda
    0.38
    तावनी
    0.37
     Españ
    0.37
     περισσότε
    0.37
    
    0.37
    POSITIVE LOGITS
    ysel
    0.41
     n
    0.40
    perms
    0.39
    perm
    0.38
    ïne
    0.38
    verbal
    0.38
     elle
    0.38
    gri
    0.38
    kala
    0.38
    kale
    0.37
    Activations Density 0.000%

    No Known Activations