© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 6354
    Prev
    Next
    INDEX
    Explanations

    count or probability

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

    boxed answers or final results

    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
    ��
    0.43
    <'
    0.40
     Emoji
    0.39
    gle
    0.39
     mait
    0.38
     uda
    0.38
     emoji
    0.37
     reff
    0.37
    jung
    0.36
     👌
    0.36
    POSITIVE LOGITS
    }\,
    0.55
     \,\
    0.54
     \,
    0.54
    }\!\
    0.52
    }}{\
    0.52
    }}\\
    0.52
    }\\
    0.50
     }$
    0.50
     \;
    0.48
    }$\\
    0.48
    Activations Density 0.003%

    No Known Activations