© 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. 76651
    Prev
    Next
    INDEX
    Explanations

    two albums

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

    focusing on specific roles

    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
     '#
    0.49
    :#
    0.46
    #'
    0.45
     on
    0.44
     #{@
    0.43
    юза
    0.43
    죠
    0.42
    নার্থ
    0.42
    "
    0.41
    :
    0.41
    POSITIVE LOGITS
     ಸೇ
    0.54
     Chiến
    0.52
    ࢮ
    0.52
     Σε
    0.50
     Bảo
    0.50
     香
    0.50
     Shall
    0.49
     Besonders
    0.49
     প্রাধান্য
    0.49
     Πολ
    0.49
    Activations Density 0.001%

    No Known Activations