© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 6244
    Prev
    Next
    INDEX
    Explanations

    programmed to be helpful

    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
     下
    0.64
     mü
    0.62
    无论是
    0.61
     current
    0.59
     present
    0.58
     conversation
    0.58
     না
    0.56
    ьи
    0.56
    distance
    0.56
     race
    0.55
    POSITIVE LOGITS
     größ
    0.92
     bruta
    0.83
    ጳ
    0.83
     ؛
    0.82
     bruto
    0.81
     ৪র্থ
    0.79
     ventured
    0.79
    .;
    0.79
     anarchy
    0.78
     வீட்டு
    0.78
    Activations Density 0.029%

    No Known Activations