© 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. 223198
    Prev
    Next
    INDEX
    Explanations

    common connectors

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

    **oc** **lette** **console** **drying** **listen**

    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
    </code>
    0.47
    ?\
    0.46
    ENGE
    0.45
    ₺
    0.44
    猀
    0.44
    म्मद
    0.44
     hydrochloride
    0.44
     zove
    0.42
    ISTAN
    0.42
     malos
    0.42
    POSITIVE LOGITS
     소
    0.54
     სა
    0.48
     기초
    0.48
     공동
    0.47
    ที่จะ
    0.47
     እንደሚ
    0.45
     চলতি
    0.45
     Electroly
    0.44
     Пра
    0.43
     다니
    0.43
    Activations Density 0.001%

    No Known Activations