© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 2807
    Prev
    Next
    INDEX
    Explanations

    code snippets and structured data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-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
    л
    0.86
    ので
    0.76
    "
    0.75
     disso
    0.73
    ం
    0.71
    ം
    0.70
    ook
    0.70
    т
    0.69
    BeginInit
    0.68
    ễn
    0.67
    POSITIVE LOGITS
     PREFIX
    1.05
     testclass
    1.04
     الهمزه
    1.04
    ◑
    1.04
    ィ
    1.02
     forState
    1.01
     hatchback
    1.01
    s
    1.01
    রিদ
    1.01
    nın
    1.01
    Activations Density 0.287%

    No Known Activations