© 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. 131225
    Prev
    Next
    INDEX
    Explanations

    Gigabit speeds

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

    requests, though, custom, constant, not, generated

    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
     x
    0.53
    /**
    0.53
    ты
    0.49
    }){
    0.48
    ћ
    0.48
    х
    0.47
    ствия
    0.46
    쑤
    0.46
    ivanja
    0.46
     पृ
    0.45
    POSITIVE LOGITS
    etrain
    0.47
     Besonder
    0.46
    રો
    0.45
    ่อย
    0.44
     விதி
    0.44
     antifer
    0.44
    magnet
    0.44
     મુદ્
    0.44
     মৌসুম
    0.43
    Magnet
    0.42
    Activations Density 0.000%

    No Known Activations