© 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. 121367
    Prev
    Next
    INDEX
    Explanations

    harvesting and downloading

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

    historical figures 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
    プロ
    0.53
    tiene
    0.52
    ಿದರೆ
    0.52
    logan
    0.51
    une
    0.47
    본
    0.46
    لاميذ
    0.46
    프
    0.46
    वारा
    0.45
    ieht
    0.45
    POSITIVE LOGITS
     Zeus
    0.56
     enlarged
    0.55
     weakened
    0.54
     Star
    0.53
     Scan
    0.53
     SCAN
    0.53
     scanned
    0.52
     Odin
    0.52
     Packet
    0.51
     Chaucer
    0.51
    Activations Density 0.001%

    No Known Activations