© 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. 130955
    Prev
    Next
    INDEX
    Explanations

    thank you and russian text

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

    city names and environments

    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
    ür
    0.55
    -
    0.49
     डों
    0.49
    orms
    0.48
    ention
    0.48
     कां
    0.48
    ucose
    0.47
    residents
    0.46
    omb
    0.46
    ➠
    0.46
    POSITIVE LOGITS
     flashbacks
    0.46
     qRT
    0.44
     FUTURE
    0.43
     lograron
    0.42
     gzip
    0.42
     ROYAL
    0.40
    يم
    0.40
    ভুক্ত
    0.40
     عالم
    0.40
    Ро
    0.40
    Activations Density 0.001%

    No Known Activations