© 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. 11573
    Prev
    Next
    INDEX
    Explanations

    special characters and puncutation

    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
    en
    2.86
     patties
    2.24
    itriangular
    2.15
    瑁
    2.15
     якого
    2.11
     fain
    2.09
    coming
    2.09
     pale
    2.08
     pulgadas
    2.06
     入れ
    2.01
    POSITIVE LOGITS
    elseif
    2.24
    даги
    1.99
    ಿರುವ
    1.98
     alem
    1.92
    informed
    1.85
    👏👏
    1.83
    garakan
    1.82
     वाजिब
    1.80
     annoyed
    1.80
    }=\
    1.78
    Activations Density 0.000%

    No Known Activations