© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 49547
    Prev
    Next
    INDEX
    Explanations

    sides

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     äußerst
    0.42
     à
    0.39
     AAU
    0.38
     prácticamente
    0.38
     ihnen
    0.37
     übrigens
    0.37
    SIBILITY
    0.37
    υνα
    0.36
    ત્મ
    0.36
    èse
    0.36
    POSITIVE LOGITS
     marcas
    0.42
    푦
    0.41
     पचास
    0.40
    രുടെയും
    0.40
    astanza
    0.40
     左
    0.39
     изображения
    0.39
    食べる
    0.36
    左
    0.36
     অফিসের
    0.36
    Activations Density 0.001%

    No Known Activations