© 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-16K
    7. 12364
    Prev
    Next
    INDEX
    Explanations

    Q followed by numbers or starting words

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

    Q followed by u, numbers, or punctuation

    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_16k_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
    ג
    0.76
    ugan
    0.59
    وك
    0.59
    ва
    0.59
     (
    0.55
    지와
    0.55
    ją
    0.54
    اؤن
    0.53
    دت
    0.52
    گ
    0.52
    POSITIVE LOGITS
    Q
    1.09
    Ｑ
    1.00
     q
    0.98
    𝑄
    0.91
     Q
    0.91
    NQ
    0.88
     Qo
    0.87
    IQ
    0.86
    Qw
    0.84
     Qa
    0.83
    Activations Density 0.432%

    No Known Activations