© 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. 246295
    Prev
    Next
    INDEX
    Explanations

    foreign words, specific items, or following common prepositions

    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
     결혼
    0.48
    芴
    0.48
     반려
    0.46
    ᑖ
    0.46
    萘
    0.45
     دعوت
    0.45
    EOUS
    0.45
    曷
    0.44
     अतः
    0.44
     발전
    0.44
    POSITIVE LOGITS
     withheld
    0.49
     them
    0.47
     খে
    0.46
     particularly
    0.45
     них
    0.44
     especialmente
    0.42
     vooral
    0.42
     pegged
    0.42
     cayenne
    0.41
     striped
    0.40
    Activations Density 0.001%

    No Known Activations