© 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. 87809
    Prev
    Next
    INDEX
    Explanations

    suspending, aware, Land, product, awareness, time, coordinating

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

    hormonal fluctuations or cycles

    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
     LoginForm
    0.50
     Spatial
    0.48
     Bila
    0.48
     Polyg
    0.46
     Bild
    0.45
     Brasileira
    0.45
     Compact
    0.44
    🕑
    0.44
    睍
    0.44
     Different
    0.43
    POSITIVE LOGITS
    huge
    0.52
    개
    0.50
    দূত
    0.50
    MASS
    0.49
    타
    0.49
    ham
    0.47
    란
    0.47
    내
    0.47
     outweighs
    0.47
    explode
    0.46
    Activations Density 0.002%

    No Known Activations