© 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. 11461
    Prev
    Next
    INDEX
    Explanations

    moon and moonlight

    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
    м
    3.42
    م
    3.05
    टेगरी
    2.96
     surgi
    2.82
     reten
    2.74
    CNS
    2.71
     fär
    2.70
    ва
    2.61
    ി
    2.58
    ్ర
    2.55
    POSITIVE LOGITS
    ли
    3.02
    क
    2.90
    shine
    2.88
    кої
    2.73
     purnama
    2.65
    ك
    2.63
     CONTRIBUT
    2.62
    geht
    2.61
     piena
    2.60
    وأ
    2.57
    Activations Density 0.018%

    No Known Activations