© 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. 52286
    Prev
    Next
    INDEX
    Explanations

    citations and academic references

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

    when they

    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
    ים
    0.53
    ה
    0.46
    י
    0.45
    ي
    0.45
     אך
    0.45
    HOUSE
    0.44
     hym
    0.44
    し
    0.44
    HAND
    0.43
    ็
    0.43
    POSITIVE LOGITS
     চ্যাম্প
    0.55
    porque
    0.52
     모집
    0.49
     لأنه
    0.49
     प्रतिस्पर्धा
    0.49
     市場
    0.49
     porque
    0.48
    atletas
    0.48
     Porque
    0.47
    assapi
    0.47
    Activations Density 0.000%

    No Known Activations