© 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. 115532
    Prev
    Next
    INDEX
    Explanations

    planning conditional actions

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

    plans and expected timing

    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
     spricht
    0.47
    <0xA7>
    0.46
     工
    0.44
     চালাচ্ছে
    0.43
     диви
    0.42
    बर्ग
    0.42
    μπο
    0.40
    রুখ
    0.40
     тер
    0.40
    ochemistry
    0.39
    POSITIVE LOGITS
     Clipping
    0.46
     altres
    0.45
    ഢ
    0.45
    ه
    0.44
     reasonably
    0.44
     preved
    0.43
    ה
    0.43
    এখানে
    0.43
    ສໍາ
    0.42
     identific
    0.41
    Activations Density 0.001%

    No Known Activations