© 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. 9-GEMMASCOPE-2-RES-262K
    7. 11585
    Prev
    Next
    INDEX
    Explanations

    superlative 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_9_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
    times
    3.41
    e
    2.98
    erView
    2.85
    speople
    2.80
    simeq
    2.79
    lets
    2.78
    quest
    2.75
    shakes
    2.70
    ט
    2.66
    phi
    2.64
    POSITIVE LOGITS
    ই
    2.83
    ма
    2.82
    g
    2.81
    ة
    2.70
    런
    2.67
    de
    2.45
    ே
    2.43
    ەوە
    2.42
     arrivé
    2.42
    ال
    2.38
    Activations Density 0.043%

    No Known Activations