© 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. 99683
    Prev
    Next
    INDEX
    Explanations

    actions and their outcomes

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

    practical advice and cautions

    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
     посвящен
    0.54
    伟大
    0.47
    很大
    0.46
     좋아
    0.46
     मुख्यतः
    0.45
     услуги
    0.44
     стадии
    0.44
    陞
    0.43
     объяв
    0.43
     акы
    0.42
    POSITIVE LOGITS
    ())
    0.43
     doubt
    0.42
     ignor
    0.42
     ophthalm
    0.41
     err
    0.40
    terer
    0.40
     said
    0.40
     diri
    0.40
     recipiente
    0.40
     silenz
    0.40
    Activations Density 0.001%

    No Known Activations