© 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. 74017
    Prev
    Next
    INDEX
    Explanations

    specific references and locations

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

    communication is key

    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
    ᱒
    0.47
    匁
    0.47
    PING
    0.47
    POINTS
    0.46
    mites
    0.45
    rimps
    0.44
    dataIn
    0.43
    呤
    0.43
     POINTS
    0.43
    籃
    0.42
    POSITIVE LOGITS
    т
    0.52
    solution
    0.50
     Device
    0.48
     Spart
    0.47
    า
    0.47
    b
    0.47
    st
    0.47
     szczę
    0.46
    ו
    0.46
    }
    0.46
    Activations Density 0.000%

    No Known Activations