© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 13390
    Prev
    Next
    INDEX
    Explanations

    past papers, youth slang

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_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
    ূল্য
    2.10
     manglid
    2.09
    ത്തിലുള്ള
    2.04
    elementProp
    2.03
     FontFamily
    2.02
    誑
    2.00
     კიდ
    1.97
     alcun
    1.95
    HTTPSampler
    1.94
     tegas
    1.94
    POSITIVE LOGITS
    R
    1.58
    \'
    1.57
    𝐬
    1.56
    een
    1.49
    ers
    1.48
    S
    1.42
    iamond
    1.40
    t
    1.40
    ez
    1.39
    𝓮
    1.37
    Activations Density 0.000%

    No Known Activations