© 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-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 1011
    Prev
    Next
    INDEX
    Explanations

    publicly available, depending on

    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
    瀛
    0.63
    ceau
    0.59
    Ibid
    0.59
    Create
    0.59
    jose
    0.58
    isc
    0.58
     జమ
    0.57
     Corinth
    0.56
     Coppa
    0.56
    遏
    0.56
    POSITIVE LOGITS
     largely
    0.72
    utables
    0.58
     unary
    0.57
     nearly
    0.56
     sensitive
    0.55
    𝙾
    0.54
     almost
    0.53
     us
    0.53
     seemingly
    0.53
    US
    0.53
    Activations Density 0.884%

    No Known Activations