© 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. 73851
    Prev
    Next
    INDEX
    Explanations

    then other languages

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

    practice, practice, practice

    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
     સહિત
    0.45
    ः
    0.44
     maupun
    0.41
    などに
    0.41
     incluyendo
    0.40
    などの
    0.38
    ط
    0.38
    }(
    0.38
    ١
    0.38
     سمیت
    0.38
    POSITIVE LOGITS
    然后
    0.68
     然后
    0.67
     然後
    0.60
    然後
    0.54
    然后在
    0.50
    然后再
    0.49
     Rồi
    0.47
     rồi
    0.47
    Rồi
    0.45
     তারপর
    0.42
    Activations Density 0.077%

    No Known Activations