© 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. 181487
    Prev
    Next
    INDEX
    Explanations

    collection box

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

    legal consequences, pressure, connections

    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
    しさ
    0.50
    거리
    0.49
     ジ
    0.47
    ListComponent
    0.46
    🏬
    0.46
    されており
    0.46
     전략
    0.45
     вый
    0.45
    倨
    0.45
    現在は
    0.45
    POSITIVE LOGITS
    ?"
    0.44
     chiens
    0.43
    ফেট
    0.43
    errno
    0.41
     شويه
    0.41
    ຫານ
    0.41
    alm
    0.40
     davran
    0.39
     conexiones
    0.39
     svojih
    0.39
    Activations Density 0.001%

    No Known Activations