© 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. 125630
    Prev
    Next
    INDEX
    Explanations

    monolingual and multilingual categories

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

    reliability to, successful jewel, function, scoff, cultivates

    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
    كين
    0.46
     Kelly
    0.43
    下
    0.42
     Stuart
    0.42
    主持人
    0.41
    Broadcast
    0.41
    ഞ്ഞ്
    0.41
    Kelly
    0.40
    桥
    0.39
    Producer
    0.39
    POSITIVE LOGITS
     monol
    0.53
     hayvan
    0.51
     liht
    0.49
     ใคร
    0.49
     only
    0.48
     выбор
    0.47
     monochromatic
    0.46
     отече
    0.46
     berd
    0.46
     сельскохозяй
    0.46
    Activations Density 0.001%

    No Known Activations