Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 7572
    Prev
    Next
    INDEX
    Explanations

    's or 't' endings

    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
    u
    1.47
    us
    1.27
    ت
    1.16
    es
    1.15
    iselt
    1.09
    a
    1.09
     Люди
    1.09
    ire
    1.08
     magnum
    1.05
    })-
    1.04
    POSITIVE LOGITS
    arovski
    1.53
    ARIO
    1.47
    úp
    1.36
    adresse
    1.33
     naby
    1.30
    exercice
    1.29
    ochlor
    1.28
    하고
    1.24
    lerin
    1.24
    Absolutely
    1.24
    Activations Density 0.089%

    No Known Activations