© 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. 97577
    Prev
    Next
    INDEX
    Explanations

    White Dove Releases

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

    production facility, concept of, largest vaulted

    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
    asks
    0.46
     quits
    0.43
    p
    0.43
     갈
    0.43
    }_{+}
    0.43
    }^{+}\
    0.42
     admits
    0.42
    og
    0.42
     Thái
    0.42
    extreme
    0.41
    POSITIVE LOGITS
     Accessories
    0.50
     TNFR
    0.50
     Aspergillus
    0.50
    🧁
    0.48
    Description
    0.48
     HDAC
    0.47
     YOU
    0.47
     HAPPY
    0.47
    ্লিকেশন
    0.47
     Compatibility
    0.47
    Activations Density 0.001%

    No Known Activations