© 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. 11548
    Prev
    Next
    INDEX
    Explanations

    acceptance, honor, Auschwitz

    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
     limbs
    1.62
    ed
    1.59
    я
    1.58
     numérica
    1.57
    ة
    1.47
     tankers
    1.47
     unitarity
    1.45
     bijective
    1.44
     phospho
    1.43
     retângulo
    1.42
    POSITIVE LOGITS
    ع
    1.82
    必要がある
    1.69
    実践
    1.61
    er
    1.61
    ן
    1.60
     Towa
    1.56
     IW
    1.53
    এদিকে
    1.50
     hastened
    1.48
     IRA
    1.48
    Activations Density 0.001%

    No Known Activations