© 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. 38786
    Prev
    Next
    INDEX
    Explanations

    understanding

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

    playbook, loader setup, city, digital painting, monsters, miso, number

    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
     to
    0.49
     material
    0.46
    로
    0.46
     forces
    0.43
     chancellor
    0.43
     bowels
    0.43
     man
    0.42
     institutes
    0.42
     generales
    0.42
     mano
    0.41
    POSITIVE LOGITS
     كبير
    0.50
    w
    0.50
    ской
    0.49
    стів
    0.49
     แก้
    0.48
    isierte
    0.47
    ส์
    0.47
    簸
    0.47
     島
    0.47
     hooked
    0.46
    Activations Density 0.000%

    No Known Activations