© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 244348
    Prev
    Next
    INDEX
    Explanations

    specifications or transactional details

    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
    a
    0.49
     sod
    0.46
    outro
    0.44
    ગ
    0.42
     яв
    0.41
    ar
    0.41
    aza
    0.41
    hum
    0.41
    artig
    0.41
    akim
    0.41
    POSITIVE LOGITS
     avoids
    0.49
    >^
    0.49
     overlooking
    0.48
    ;}
    0.47
    >'
    0.47
    🐆
    0.45
     অধিকাংশই
    0.45
    >-
    0.45
    🏗
    0.45
     avoid
    0.45
    Activations Density 0.001%

    No Known Activations