© 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. 75729
    Prev
    Next
    INDEX
    Explanations

    housing areas, conventional rate, permit roll

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

    specific keywords followed by common conjunctions

    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
    ורים
    0.59
    веден
    0.52
     עד
    0.52
     вари
    0.51
     அரை
    0.51
    вари
    0.50
    ফলে
    0.50
     новая
    0.49
    }";
    0.48
     ампли
    0.48
    POSITIVE LOGITS
     mechanical
    0.52
     perturbed
    0.52
     venting
    0.50
    essa
    0.50
     bat
    0.47
     projected
    0.47
    istä
    0.47
    uring
    0.47
     hosp
    0.47
     bout
    0.47
    Activations Density 0.001%

    No Known Activations