© 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. 107314
    Prev
    Next
    INDEX
    Explanations

    Tech Products

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

    describing events and their consequences

    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
    activer
    0.53
    actively
    0.50
     distract
    0.49
     ornament
    0.49
     concealing
    0.47
    繃
    0.46
    activated
    0.45
     caché
    0.45
    ストレ
    0.44
     extinct
    0.43
    POSITIVE LOGITS
     管理
    0.47
     冬
    0.47
     Bathroom
    0.46
    槃
    0.46
     Phòng
    0.45
     Deaths
    0.45
    颐
    0.44
     เพื่อน
    0.43
    劭
    0.43
     कोणत्या
    0.43
    Activations Density 0.001%

    No Known Activations