© 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. 33184
    Prev
    Next
    INDEX
    Explanations

    approaching, reserve, respectfully

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

    upcoming advanced technologies

    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
     appended
    0.54
     proteinuria
    0.48
     সন্তানদের
    0.46
     internationalen
    0.46
    слей
    0.46
     अल्को
    0.46
    켈
    0.46
    িকপ্ট
    0.44
    חת
    0.43
    لک
    0.43
    POSITIVE LOGITS
    ffic
    0.52
     erano
    0.50
    Tempo
    0.49
    N
    0.49
    et
    0.48
    Data
    0.47
     plus
    0.47
    чила
    0.47
     matière
    0.47
    we
    0.46
    Activations Density 0.000%

    No Known Activations