© 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. 65276
    Prev
    Next
    INDEX
    Explanations

    names followed by actions

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

    introduces or discovers

    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
     vardı
    0.59
     είχε
    0.54
    不仅仅
    0.51
    格式
    0.49
     ```
    0.47
     있었다
    0.46
    从
    0.45
    输出
    0.44
    说了
    0.44
     或者
    0.44
    POSITIVE LOGITS
     natomiast
    0.60
     informed
    0.52
     accuses
    0.50
     informs
    0.49
    informed
    0.49
     জানায়
    0.48
     araw
    0.48
     ಇದರಿಂದ
    0.48
     disgust
    0.48
     accuse
    0.46
    Activations Density 0.045%

    No Known Activations