© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 9485
    Prev
    Next
    INDEX
    Explanations

    various languages

    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
     recourse
    2.02
     majoring
    1.99
     unincorporated
    1.95
     nagging
    1.90
     comentado
    1.85
     correspondingly
    1.82
    ה
    1.82
     doll
    1.80
     presque
    1.79
     pseudonym
    1.73
    POSITIVE LOGITS
    ين
    2.08
    saan
    1.96
     सभी
    1.89
    たくさん
    1.88
     وح
    1.87
     कई
    1.86
    𝐈
    1.84
    aarr
    1.83
     emberek
    1.82
     அனைத்து
    1.81
    Activations Density 0.023%

    No Known Activations