© 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. 12139
    Prev
    Next
    INDEX
    Explanations

    :

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

    variable like size

    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
    મેન્ટ
    0.51
     Kendrick
    0.47
    bole
    0.46
     Mitch
    0.46
    嘞
    0.46
     ?”
    0.45
    𝐨
    0.45
    તે
    0.45
    咱们
    0.45
    జ్‌
    0.45
    POSITIVE LOGITS
     혹은
    0.45
     peroxidase
    0.44
     Sanskrit
    0.44
     understood
    0.44
     或
    0.44
     assimilation
    0.44
     superscript
    0.43
     glossary
    0.42
    SC
    0.42
     molecules
    0.41
    Activations Density 0.000%

    No Known Activations