© 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-16K
    7. 1723
    Prev
    Next
    INDEX
    Explanations

    perfect quality descriptor

    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_16k_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
    おそらく
    3.25
    spaper
    3.17
    蔔
    2.98
    er
    2.93
    र
    2.86
     scall
    2.74
    х
    2.69
    もちろん
    2.65
     ainult
    2.65
    켜
    2.58
    POSITIVE LOGITS
    iest
    3.61
    ా
    3.02
    named
    3.02
    aan
    2.97
    o
    2.88
    т
    2.84
    UAGE
    2.81
    دون
    2.78
    يات
    2.76
    𝙙
    2.76
    Activations Density 0.190%

    No Known Activations