© 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. 201739
    Prev
    Next
    INDEX
    Explanations

    documentation, data, or creative actions

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

    powerful way

    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
     வெற்றி
    0.54
     पिटाई
    0.54
     தலைமையில்
    0.53
     समर्थन
    0.53
    =".$
    0.51
     suav
    0.50
    SUPPORT
    0.50
     എസ്
    0.50
     આજે
    0.49
     mendukung
    0.49
    POSITIVE LOGITS
     wasted
    0.49
     ,
    0.46
    一眼
    0.45
     exploits
    0.44
     athlet
    0.43
     athletic
    0.42
     identifications
    0.42
     assisting
    0.40
    来看
    0.40
     reaping
    0.40
    Activations Density 0.001%

    No Known Activations