© 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. 23698
    Prev
    Next
    INDEX
    Explanations

    Voyager spacecraft missions

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

    clot, overclock, women

    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
    JSONException
    0.43
    Cast
    0.43
    তিন
    0.43
    ใช้
    0.41
    ח
    0.39
    ix
    0.39
    א
    0.39
    焘
    0.39
    บ
    0.38
     ৫০
    0.38
    POSITIVE LOGITS
     Ayers
    0.46
     odnos
    0.46
     fairly
    0.44
     wont
    0.44
     plight
    0.44
     storyboard
    0.44
     obie
    0.43
     entsprechenden
    0.43
     obje
    0.43
     eases
    0.43
    Activations Density 0.000%

    No Known Activations