© 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-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 30488
    Prev
    Next
    INDEX
    Explanations

    range indicator

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     approximate
    0.46
     approximately
    0.46
     approxim
    0.44
     etc
    0.40
     approximated
    0.38
     approx
    0.38
    "-"
    0.38
     roughly
    0.38
     மட்டும்
    0.38
     uncont
    0.37
    POSITIVE LOGITS
     क्विंटल
    0.48
     (>
    0.46
     असंख्य
    0.42
     وحتى
    0.41
    гүй
    0.40
     Till
    0.40
     حتی
    0.40
     هستند
    0.39
    യുള്ള
    0.39
    ವೇ
    0.39
    Activations Density 0.002%

    No Known Activations