© 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. 53032
    Prev
    Next
    INDEX
    Explanations

    rights to

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

    partner, exclusives, cultivars, relationship

    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
    ез
    0.49
     あれ
    0.48
     因为
    0.48
    检验
    0.47
    ű
    0.47
    чных
    0.46
    颶
    0.46
    াবণ
    0.46
    вшись
    0.46
    ла
    0.46
    POSITIVE LOGITS
     derivadas
    0.49
    s
    0.46
    マーケ
    0.45
    RECE
    0.44
    ตลาด
    0.44
    সুতরাং
    0.43
     deriv
    0.43
     receivable
    0.43
     KYC
    0.42
    compre
    0.42
    Activations Density 0.000%

    No Known Activations