© 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. 212440
    Prev
    Next
    INDEX
    Explanations

    geographical locations and events

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

    providing details

    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
    Ⲕ
    0.59
    ка
    0.48
     Зе
    0.48
    Satisfaction
    0.47
    ベクトル
    0.46
    レル
    0.46
     Magde
    0.45
    Ἱ
    0.45
     собою
    0.44
     اشک
    0.44
    POSITIVE LOGITS
     \
    0.54
     informs
    0.52
    interesting
    0.52
     informed
    0.49
    assa
    0.49
    莫名
    0.48
    ments
    0.48
    in
    0.47
    lista
    0.47
    拥有
    0.47
    Activations Density 0.001%

    No Known Activations