© 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. 58352
    Prev
    Next
    INDEX
    Explanations

    father is, Turkish ), here ., to go

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

    Suitable Target

    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
     lLoginID
    0.52
    ®.
    0.51
     acabado
    0.48
    เหลือ
    0.46
    AllResult
    0.46
     leuk
    0.46
     sendiri
    0.46
     wszystkich
    0.45
     fertig
    0.45
     wabarakatuh
    0.45
    POSITIVE LOGITS
    ං
    0.43
    拉斯
    0.43
     Emotions
    0.41
    o
    0.40
    超
    0.40
    edy
    0.40
    霧
    0.40
    erap
    0.39
    ял
    0.39
    েরা
    0.39
    Activations Density 0.000%

    No Known Activations