© 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. 16880
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

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

    delimiting characters

    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
    ister
    0.37
    com
    0.36
     com
    0.34
    with
    0.34
     cameras
    0.33
    Com
    0.33
    file
    0.33
                          
    0.32
     $\
    0.32
     casein
    0.32
    POSITIVE LOGITS
     però
    0.36
    酆
    0.36
    อะ
    0.36
     Scary
    0.35
     nennen
    0.35
    WeakTable
    0.34
    骢
    0.34
     près
    0.33
     vicino
    0.33
     seiner
    0.33
    Activations Density 0.000%

    No Known Activations