© 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. 69303
    Prev
    Next
    INDEX
    Explanations

    end. weekend, ahead of

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

    quality varies

    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
    线条
    0.42
     chứa
    0.41
     مُ
    0.41
    <h5>
    0.40
     unassuming
    0.40
     숨
    0.39
    隐藏
    0.39
    ()){
    0.38
     bề
    0.38
    isHidden
    0.38
    POSITIVE LOGITS
    當時
    0.52
    ptions
    0.51
     नंतर
    0.51
     pouv
    0.50
     তবু
    0.50
     pouvaient
    0.49
     Nevertheless
    0.49
     tuto
    0.48
     όμως
    0.48
    メリカ
    0.48
    Activations Density 0.002%

    No Known Activations