© 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. 150609
    Prev
    Next
    INDEX
    Explanations

    foreign language words, timestamps, packaging

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

    passive voice, footnotes referencing, players specializing, SaaS products

    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
    దాయ
    0.50
    ى
    0.46
    闿
    0.46
    ভাগ
    0.45
    ím
    0.44
     በጣም
    0.44
    برى
    0.44
    긍
    0.44
     बनाकर
    0.43
     vielen
    0.43
    POSITIVE LOGITS
     timestamps
    0.46
    IntValue
    0.45
     ذریع
    0.44
     waist
    0.43
     되겠죠
    0.43
    民眾
    0.42
     Derived
    0.42
     pazienti
    0.42
     lysates
    0.41
     Букови
    0.40
    Activations Density 0.001%

    No Known Activations