© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12418
    Prev
    Next
    INDEX
    Explanations

    SEC filings and loan documents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
    िल
    1.82
    ビ
    1.67
    プレ
    1.66
    デン
    1.63
    alé
    1.57
    intellij
    1.56
    ဗ
    1.55
    íes
    1.54
    イル
    1.53
    യില
    1.53
    POSITIVE LOGITS
    guas
    1.58
    ו
    1.58
    gms
    1.55
    np
    1.52
     শ্রেণীর
    1.49
    GFS
    1.44
    號
    1.44
     Parties
    1.43
    kers
    1.39
    gua
    1.39
    Activations Density 0.000%

    No Known Activations