© 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. 211202
    Prev
    Next
    INDEX
    Explanations

    eight feet, learning foreign, signals falling

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

    AI models

    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
     الجذر
    0.48
    innerHTML
    0.46
    })$
    0.43
     mRNAs
    0.43
     censored
    0.43
     unpublished
    0.42
    }=
    0.41
    暑
    0.41
    考察
    0.41
    }).
    0.40
    POSITIVE LOGITS
     backdrop
    0.54
     असलेल्या
    0.49
     intently
    0.48
    Xin
    0.46
    iis
    0.46
    rester
    0.45
    ureate
    0.45
    plast
    0.45
    as
    0.45
    viation
    0.43
    Activations Density 0.000%

    No Known Activations