© 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
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 226
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation

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

    .zip, .dev, 7-zip

    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
    signed
    0.27
    效
    0.26
    scripts
    0.25
    కు
    0.24
    displacement
    0.24
    inscription
    0.24
    agricultural
    0.24
    polynomial
    0.24
    dependencies
    0.24
    மற்ற
    0.24
    POSITIVE LOGITS
    ristmas
    0.36
     cyberspace
    0.30
    ۹
    0.30
    ivirus
    0.29
    ੦
    0.29
    maire
    0.29
    ..."
    0.29
    leine
    0.29
    -...
    0.28
    .......
    0.28
    Activations Density 0.106%

    No Known Activations