© 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. 58658
    Prev
    Next
    INDEX
    Explanations

    terms and legal text

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

    more secular, faster, greater muscular, depicts Moses

    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
     volcanoes
    0.43
    ٠
    0.42
     निकाली
    0.42
     grated
    0.41
     volcano
    0.40
     beneficial
    0.40
     Beneficial
    0.40
     Ç
    0.40
    ០
    0.40
    Assim
    0.39
    POSITIVE LOGITS
    তই
    0.55
    っくり
    0.54
    źdz
    0.50
     współpracy
    0.48
    Delay
    0.47
     prawidł
    0.47
    ാമ
    0.46
     покер
    0.46
    یه
    0.45
     টেল
    0.45
    Activations Density 0.000%

    No Known Activations