© 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. 11027
    Prev
    Next
    INDEX
    Explanations

    1+1 mathematics

    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
     diberi
    2.03
     mendukung
    1.86
     hükü
    1.81
    師
    1.81
     গতি
    1.81
     baza
    1.79
    师
    1.75
    ៊ី
    1.75
     foothold
    1.74
     dienst
    1.74
    POSITIVE LOGITS
    นิด
    1.99
    at
    1.93
    an
    1.84
    ان
    1.79
    ності
    1.77
    น
    1.77
    larda
    1.72
    a
    1.72
    et
    1.63
    eV
    1.61
    Activations Density 0.004%

    No Known Activations