© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 3020
    Prev
    Next
    INDEX
    Explanations

    man took, speakers,

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

    drinks deep will

    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_53_width_65k_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
     ذریع
    0.67
    》。
    0.63
    '।
    0.57
    )।
    0.57
    ].
    0.56
     کی۔
    0.56
    ]।
    0.56
    ’।
    0.55
    "/>.
    0.55
    ());
    0.53
    POSITIVE LOGITS
     has
    1.16
     deserves
    1.05
     seems
    1.03
     undergoes
    0.98
     exemplifies
    0.98
     appears
    0.96
     differs
    0.96
     έχει
    0.93
     suffers
    0.91
     resonates
    0.91
    Activations Density 0.895%

    No Known Activations