© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 56724
    Prev
    Next
    INDEX
    Explanations

    trash, bin, located, Academy, bonus feature

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

    connects ideas

    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
    Negative Logits
    Ᏺ
    0.51
    దాయ
    0.49
    Bathroom
    0.47
     až
    0.46
    Foot
    0.45
     welchem
    0.45
    ()).
    0.44
     snar
    0.44
    彼
    0.44
     wahr
    0.43
    POSITIVE LOGITS
    orescence
    0.47
    css
    0.46
    opent
    0.46
    în
    0.44
     resumo
    0.44
    opot
    0.44
    com
    0.44
    count
    0.43
    place
    0.43
    como
    0.43
    Activations Density 0.000%

    No Known Activations