© 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. 14568
    Prev
    Next
    INDEX
    Explanations

    Among the

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

    knowledge and concepts

    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
    Epid
    0.44
    s
    0.43
    </h3>
    0.42
     schema
    0.42
     Schema
    0.42
     creciente
    0.41
    los
    0.40
    Ap
    0.40
    u
    0.40
    erton
    0.40
    POSITIVE LOGITS
     safegu
    0.50
     καν
    0.49
    CBPeripheral
    0.48
     ہی
    0.48
     ሂ
    0.48
    थल
    0.48
     द्वि
    0.48
     ולה
    0.48
    厙
    0.48
    沨
    0.47
    Activations Density 0.000%

    No Known Activations