© 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. 233118
    Prev
    Next
    INDEX
    Explanations

    specific words or punctuation

    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
    M
    0.53
    G
    0.53
    D
    0.50
    L
    0.50
     ചേ
    0.49
     sea
    0.47
    sea
    0.47
    ="
    0.46
     atop
    0.45
    Zimbabwe
    0.45
    POSITIVE LOGITS
     límites
    0.52
     IEnumerator
    0.51
     கட்டடக்கலை
    0.50
    ertid
    0.49
     spirals
    0.49
     ограничения
    0.48
     प्रारंभिक
    0.48
    ’).
    0.48
    ोत्सव
    0.47
    िकारक
    0.47
    Activations Density 0.001%

    No Known Activations