© 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. 116662
    Prev
    Next
    INDEX
    Explanations

    Late check-in

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

    choice or deliberate preference

    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
     ugljik
    0.52
    inFile
    0.50
     এফ
    0.50
    দিনে
    0.47
     movimenti
    0.47
     abband
    0.47
     ড্র
    0.46
     戸
    0.46
    nave
    0.46
     防止
    0.45
    POSITIVE LOGITS
    -
    0.64
    a
    0.60
    :
    0.60
    ↵↵
    0.59
     -
    0.58
     a
    0.50
    ت
    0.49
     T
    0.48
    .
    0.48
    س
    0.48
    Activations Density 0.001%

    No Known Activations