© 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. 11883
    Prev
    Next
    INDEX
    Explanations

    margins and margin sampling

    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
    ../../
    2.08
    Commenting
    1.98
    grimas
    1.88
    known
    1.82
    ../../../
    1.82
     mentored
    1.80
    વાર
    1.76
    cerr
    1.73
    neath
    1.72
    ','"+
    1.72
    POSITIVE LOGITS
    ت
    2.41
    ر
    2.28
    ल
    2.22
     waktu
    2.11
    Autowired
    2.09
    तून
    2.08
     sheer
    2.07
    طار
    2.05
    quele
    2.04
     осуществля
    2.04
    Activations Density 0.017%

    No Known Activations