© 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. 182100
    Prev
    Next
    INDEX
    Explanations

    troubleshooting, analyzed, trend, without, anymore

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

    technical terms and code examples

    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
    "})
    0.50
    </caption>
    0.46
     Теперь
    0.45
    </sup>
    0.45
     نمای
    0.45
    }');
    0.44
     ظاهر
    0.44
    ylan
    0.44
    })(
    0.44
    ﹞
    0.44
    POSITIVE LOGITS
     flood
    0.51
     share
    0.48
     subscribe
    0.48
     aplicaciones
    0.48
     software
    0.47
     acheté
    0.46
    ἲ
    0.46
     inbuilt
    0.46
    ᅯ
    0.46
     abound
    0.45
    Activations Density 0.000%

    No Known Activations