© 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. 95606
    Prev
    Next
    INDEX
    Explanations

    He understands

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

    multi-step reasoning and programming

    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
     demonstrates
    0.46
     therapeut
    0.45
     pharmacology
    0.44
     estancia
    0.42
     decorations
    0.42
     showcases
    0.40
     استقبال
    0.40
    鍼
    0.40
     이것
    0.40
    トレーニング
    0.40
    POSITIVE LOGITS
     ブル
    0.48
     sesize
    0.46
     ਹ
    0.45
    नौ
    0.45
    oš
    0.45
     बेस
    0.44
     変
    0.44
     सप्टेंबर
    0.44
    㓶
    0.44
    うち
    0.43
    Activations Density 0.000%

    No Known Activations