© 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. 209327
    Prev
    Next
    INDEX
    Explanations

    starter packs, currency, competitive context

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

    SAML, mock, audience, date, autumn, chicken

    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
    לת
    0.49
     Roughly
    0.45
    銷售
    0.45
    ጠና
    0.44
    ?[
    0.44
    ގެ
    0.44
    ל
    0.43
    Removal
    0.43
    لم
    0.42
    ,[
    0.42
    POSITIVE LOGITS
     институ
    0.52
     डाव
    0.48
     warna
    0.43
     запусти
    0.42
    ukuran
    0.41
     учре
    0.41
     somme
    0.41
     traduire
    0.41
     institu
    0.41
     País
    0.41
    Activations Density 0.000%

    No Known Activations