© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 1688
    Prev
    Next
    INDEX
    Explanations

    limit, requests, Loss, you, off

    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_13_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
    Actually
    1.43
    Although
    1.32
    Ĝ
    1.30
    Additionally
    1.25
     أيضًا
    1.24
    Nevertheless
    1.23
    Nonetheless
    1.21
    although
    1.18
    Perhaps
    1.17
    Consider
    1.15
    POSITIVE LOGITS
     좋아요
    1.32
     없음
    1.26
     bagus
    1.12
     여자
    1.12
     zwier
    1.11
     등
    1.09
     sqlType
    1.08
     paura
    1.07
     lichaam
    1.06
     resTmp
    1.06
    Activations Density 0.854%

    No Known Activations