© 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-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 3437
    Prev
    Next
    INDEX
    Explanations

    38 sequence in helplines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cester
    0.66
    ades
    0.65
    getBy
    0.65
    tur
    0.64
     кет
    0.64
    誕
    0.63
    圤
    0.63
    ernum
    0.63
     Departing
    0.62
    createQuery
    0.62
    POSITIVE LOGITS
     things
    0.54
     Zor
    0.53
    ourse
    0.53
    voice
    0.52
     encamin
    0.52
     kaz
    0.52
    >().
    0.52
    ন্ত্রণ
    0.52
     dragging
    0.51
     mechanical
    0.51
    Activations Density 0.114%

    No Known Activations