© 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. 11274
    Prev
    Next
    INDEX
    Explanations

    foreign languages

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

    buy on, API gateway, keeping morale

    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
    ↵
    0.59
    ing
    0.47
    gas
    0.47
    ↵↵
    0.46
    ID
    0.45
    （
    0.45
    onite
    0.45
     Christian
    0.45
    ）
    0.45
    green
    0.44
    POSITIVE LOGITS
     phường
    0.49
     اوف
    0.46
     plufieurs
    0.46
    ஸல்
    0.46
     sencilla
    0.46
     glavni
    0.46
     levando
    0.46
    ្នក
    0.45
     ermög
    0.44
     mừng
    0.43
    Activations Density 0.000%

    No Known Activations