© 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. 3903
    Prev
    Next
    INDEX
    Explanations

    punctuation before capitalized words

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

    Homo species

    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
    ".
    0.40
     $-$
    0.38
     everybody
    0.38
     $"
    0.38
     $:
    0.37
     обстанов
    0.37
     [.
    0.37
    ществует
    0.37
     ."
    0.37
    或者是
    0.36
    POSITIVE LOGITS
    ...>
    0.39
    numpy
    0.37
    institution
    0.36
    بین
    0.34
    augmented
    0.34
    };//
    0.33
    dependencies
    0.33
    ));//
    0.33
    ↵↵↵↵↵↵↵
    0.32
    affine
    0.32
    Activations Density 0.010%

    No Known Activations