© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 13208
    Prev
    Next
    INDEX
    Explanations

    comparative adjectives

    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_262k_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
    matically
    1.56
    ्स
    1.46
    screen
    1.38
    e
    1.33
    sm
    1.29
    school
    1.29
    site
    1.27
     enough
    1.24
    tiny
    1.19
    phosphate
    1.19
    POSITIVE LOGITS
     safer
    1.18
    вис
    1.12
     πιο
    1.11
     fuller
    1.11
     busier
    1.08
     bardziej
    1.06
     더욱
    1.04
     More
    1.03
    ্সের
    1.02
    い
    1.01
    Activations Density 0.131%

    No Known Activations