© 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. 22-GEMMASCOPE-2-RES-16K
    7. 1054
    Prev
    Next
    INDEX
    Explanations

    O.ahu, OCI, 2-

    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_22_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
    ビニ
    0.88
     reasons
    0.84
    固
    0.81
     প্রাস
    0.78
     resolution
    0.78
    fetchAll
    0.76
    νες
    0.76
    稍
    0.76
    Accessor
    0.75
     পাল
    0.75
    POSITIVE LOGITS
    XYGEN
    1.23
    posite
    1.19
    paque
    1.14
    swald
    1.13
    verture
    1.12
    ysters
    1.12
    MEGA
    1.11
    olong
    1.07
    pportune
    1.06
    klahoma
    1.05
    Activations Density 0.180%

    No Known Activations