© 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. 209807
    Prev
    Next
    INDEX
    Explanations

    baby girl names

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

    sound, age, extract, generation, blurred

    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
     PARTS
    0.47
    וד
    0.45
     ITEMS
    0.45
     따라서
    0.44
     gelten
    0.44
     gilt
    0.44
     допуска
    0.43
    സ
    0.43
     Vgl
    0.43
     ある
    0.43
    POSITIVE LOGITS
    avo
    0.52
    janja
    0.50
     ito
    0.47
    contiguous
    0.46
    uvo
    0.46
    avax
    0.46
    img
    0.45
    ifstream
    0.45
    rivate
    0.45
    ⋅
    0.44
    Activations Density 0.000%

    No Known Activations