© 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. 15898
    Prev
    Next
    INDEX
    Explanations

    speaking about others' actions

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

    continuation and explanation

    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
    濕
    0.49
    赋
    0.45
    參加
    0.44
     욕
    0.41
    িখিত
    0.40
     대회
    0.40
    参加
    0.39
    IGNED
    0.39
    太子
    0.38
    饥
    0.38
    POSITIVE LOGITS
     provocar
    0.51
     explanatory
    0.50
     weiter
    0.50
     smug
    0.48
     explanations
    0.47
     weiterhin
    0.46
     explicación
    0.45
     persist
    0.44
     provocative
    0.44
     trium
    0.44
    Activations Density 0.093%

    No Known Activations