© 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. 143276
    Prev
    Next
    INDEX
    Explanations

    donate button

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

    avoid stuffing content

    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
     политики
    0.47
     BEFORE
    0.43
     AVG
    0.42
    ,
    0.42
     осмо
    0.42
     mayors
    0.41
     LEFT
    0.40
     FLE
    0.40
     первую
    0.39
     мной
    0.39
    POSITIVE LOGITS
    荥
    0.51
    表达式
    0.50
    станти
    0.48
    తి
    0.47
     آف
    0.47
     کورٹ
    0.46
    Equations
    0.46
    eweg
    0.44
    缑
    0.44
    Dieses
    0.44
    Activations Density 0.001%

    No Known Activations