© 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. 35318
    Prev
    Next
    INDEX
    Explanations

    repetitive units or stages

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

    step by step

    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
    pf
    0.52
    ants
    0.52
    GL
    0.52
    es
    0.50
    N
    0.50
    T
    0.49
    orns
    0.49
     pions
    0.49
    lands
    0.49
    lat
    0.48
    POSITIVE LOGITS
     系列
    0.56
     없어
    0.55
    ในปี
    0.54
     அளவில்
    0.54
    」，
    0.52
    שׁ
    0.52
     নয়
    0.51
    没什么
    0.50
     различ
    0.50
    朲
    0.49
    Activations Density 0.042%

    No Known Activations