© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 10040
    Prev
    Next
    INDEX
    Explanations

    unique identifier

    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
    та
    3.33
     inversa
    3.03
    ℎ
    2.93
    ಿಂದ
    2.78
    aplic
    2.73
    ज
    2.72
     erythematosus
    2.71
    ोत्
    2.70
     eject
    2.59
     getopt
    2.58
    POSITIVE LOGITS
    र्गत
    3.10
    ő
    2.62
    ς
    2.54
    ן
    2.47
    ীয়
    2.44
    Gesch
    2.41
    ené
    2.40
    i
    2.40
    ங்கிணை
    2.38
    MongoDB
    2.37
    Activations Density 0.012%

    No Known Activations