© 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. 156862
    Prev
    Next
    INDEX
    Explanations

    past and future actions

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

    pronouns and 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
    ่า
    0.44
     Recruiting
    0.43
    ”
    0.43
     integrado
    0.41
    PTV
    0.41
    residents
    0.41
     Liability
    0.40
    ින්
    0.40
     Lian
    0.40
    FLP
    0.39
    POSITIVE LOGITS
    öffentlichung
    0.57
     ജെ
    0.56
     색
    0.53
     ಎಲ್ಲ
    0.50
     ОС
    0.50
     цвет
    0.50
     மா
    0.49
     ഇത്
    0.48
     стра
    0.47
     എ
    0.46
    Activations Density 0.000%

    No Known Activations