© 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. 11849
    Prev
    Next
    INDEX
    Explanations

    book citations and ISBNs

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

    books and identifiers

    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
    E
    0.61
    when
    0.59
     when
    0.57
    S
    0.57
    B
    0.57
    OK
    0.55
    e
    0.54
    M
    0.54
    ’
    0.54
    OD
    0.53
    POSITIVE LOGITS
     фаразлары
    0.54
    <end_of_turn>
    0.54
     ouvrage
    0.53
     ইলেক্ট্রোড
    0.53
    湎
    0.52
     গ্রন্থ
    0.50
     книга
    0.50
    㮍
    0.50
    𒅴
    0.50
     произведение
    0.49
    Activations Density 0.004%

    No Known Activations