© 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. 62290
    Prev
    Next
    INDEX
    Explanations

    reason at, balance card, he wakes

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

    transitive verbs

    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
    人形
    0.48
     dolly
    0.47
     bonito
    0.46
     datetime
    0.45
     車
    0.44
     धातु
    0.43
    物が
    0.43
     keratin
    0.43
     kiln
    0.43
     fény
    0.43
    POSITIVE LOGITS
    getBlueTeam
    0.47
     पीएफआई
    0.44
    忉
    0.44
    чем
    0.43
     воспомина
    0.43
     confrontations
    0.42
     findPlayer
    0.42
     సమా
    0.42
    ወ
    0.42
    чане
    0.41
    Activations Density 0.000%

    No Known Activations