© 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. 178829
    Prev
    Next
    INDEX
    Explanations

    aged over, well offer, each week

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

    Global internet access, education, and collaboration

    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
     (
    0.45
    ер
    0.44
    น
    0.43
    १
    0.43
    ва
    0.43
    ема
    0.42
    ­
    0.42
    д
    0.41
    द
    0.41
    ะ
    0.41
    POSITIVE LOGITS
    leadsto
    0.49
     Toolbox
    0.48
     toolkit
    0.47
     colaboración
    0.47
     സെക്ര
    0.45
    ﯼ
    0.45
     Development
    0.45
     ডেভেলপ
    0.45
    Development
    0.45
    বৃহ
    0.45
    Activations Density 0.001%

    No Known Activations