© 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. 120316
    Prev
    Next
    INDEX
    Explanations

    years of publication

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

    multiple domains and languages

    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
    न
    0.56
    多くの
    0.52
    す
    0.52
    ल
    0.50
    ဝ
    0.50
    വൈ
    0.50
    स
    0.50
    사
    0.49
    फार
    0.49
    സ
    0.49
    POSITIVE LOGITS
     ergeben
    0.49
     Initially
    0.47
    statistik
    0.45
    legenheit
    0.44
     пут
    0.42
    明显
    0.41
    prochen
    0.41
    ądź
    0.41
     เช่น
    0.41
     θερ
    0.41
    Activations Density 0.001%

    No Known Activations