© 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. 22246
    Prev
    Next
    INDEX
    Explanations

    al fresco, Albeit, al-hands

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

    CSS layout properties

    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
    Idaho
    0.43
    <unused17>
    0.42
    র্ম
    0.41
    活动的
    0.41
    ອບ
    0.39
     কার্যকলাপ
    0.38
     என்பதற்கு
    0.38
    fbox
    0.38
    र्ण
    0.38
     চৌ
    0.38
    POSITIVE LOGITS
    •
    0.46
     Desde
    0.45
     Primeiro
    0.44
    ​​​​
    0.44
     Erik
    0.44
     Eric
    0.44
     Primero
    0.43
     Afro
    0.43
     Projeto
    0.43
    </span>
    0.42
    Activations Density 0.000%

    No Known Activations