© 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. 16618
    Prev
    Next
    INDEX
    Explanations

    and link to content

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

    `Following`, `Companies`, `Future`, `Assessment`, `Components`, `CI`

    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
     climatique
    0.42
     dialysis
    0.42
     hitter
    0.41
     tillage
    0.40
    玄
    0.40
     deletion
    0.39
     responders
    0.39
     玄
    0.39
     play
    0.38
     supplementary
    0.38
    POSITIVE LOGITS
     Meade
    0.49
     Hala
    0.47
    склю
    0.45
     обре
    0.42
     Hal
    0.41
     Komple
    0.41
     Raha
    0.40
     इतनी
    0.39
     Missions
    0.39
    Keefe
    0.39
    Activations Density 0.000%

    No Known Activations