© 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. 106992
    Prev
    Next
    INDEX
    Explanations

    our site

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

    contextual understanding

    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
    専門店
    0.50
    綻
    0.50
     Transport
    0.49
    িৎ
    0.49
    ષ્ણા
    0.47
    ui
    0.46
    Transport
    0.45
    നേ
    0.45
     Optics
    0.45
     IOP
    0.45
    POSITIVE LOGITS
     البسط
    0.47
     п
    0.47
     الدا
    0.46
     fervent
    0.46
     ardent
    0.46
     p
    0.45
     hebben
    0.45
     تكلم
    0.45
     juillet
    0.44
    rugg
    0.44
    Activations Density 0.000%

    No Known Activations