© 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. 3058
    Prev
    Next
    INDEX
    Explanations

    LLMs

    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
     arrowhead
    0.76
     खु
    0.68
     cape
    0.67
    悦
    0.67
    ष्ठी
    0.66
     Single
    0.66
    東北
    0.65
    hab
    0.65
     Nord
    0.64
     tick
    0.64
    POSITIVE LOGITS
    M
    0.96
    Mm
    0.85
    म
    0.84
    Μ
    0.84
    Nm
    0.77
     modelos
    0.77
     Μ
    0.77
    m
    0.76
    mt
    0.76
     reciben
    0.76
    Activations Density 0.043%

    No Known Activations