© 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. 73376
    Prev
    Next
    INDEX
    Explanations

    opportunity, complaining, price, experience, restricted, restricts

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

    diagnose or alternatives

    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
    r
    0.52
    DE
    0.48
    ر
    0.48
    large
    0.47
     Kleine
    0.44
     "
    0.42
    funded
    0.42
    df
    0.41
     DE
    0.41
    ꯑ
    0.41
    POSITIVE LOGITS
     esfor
    0.53
    的重要性
    0.51
    स्कृतिक
    0.49
    㓞
    0.47
     allError
    0.47
    𝒞
    0.47
    udent
    0.47
    𝙻
    0.46
     bona
    0.46
     bună
    0.46
    Activations Density 0.001%

    No Known Activations