© 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. 151365
    Prev
    Next
    INDEX
    Explanations

    legal jurisdiction and contracts

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

    list markers or conversational openers

    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
    V
    0.45
    投影
    0.45
    规划
    0.43
    Colour
    0.42
     그래서
    0.41
    Hv
    0.41
    ศิลป
    0.41
    暧
    0.40
    便
    0.40
    Musical
    0.39
    POSITIVE LOGITS
     চেয়ে
    0.48
     individuais
    0.46
     informacion
    0.46
     comandante
    0.45
     ansiedad
    0.43
     adenovirus
    0.43
    ಳ್
    0.43
     senador
    0.43
     porcentaje
    0.43
     Türkei
    0.43
    Activations Density 0.001%

    No Known Activations