© 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. 76733
    Prev
    Next
    INDEX
    Explanations

    Premier League and jersey names

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

    bat and ball problem

    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
     তাহাদিগের
    0.53
    脚
    0.49
    
    0.47
     বলিলাম
    0.46
     विशेष
    0.45
     zmniejs
    0.44
    marriage
    0.44
    ใช้
    0.43
     ご
    0.43
     ลด
    0.43
    POSITIVE LOGITS
    indle
    0.43
     bores
    0.42
     arrays
    0.42
    healthy
    0.42
     hurricane
    0.40
     puta
    0.39
     mortals
    0.39
     vezes
    0.39
    టై
    0.39
     అలీ
    0.39
    Activations Density 0.002%

    No Known Activations