© 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. 10895
    Prev
    Next
    INDEX
    Explanations

    Pacific Northwest geography

    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
    ة
    2.96
    ை
    2.87
    𝐢
    2.81
    ड
    2.79
    LEMENT
    2.72
    mog
    2.60
    ed
    2.56
    я
    2.55
     sabb
    2.55
    եռ
    2.53
    POSITIVE LOGITS
    𝗟
    3.56
    𝗥
    3.28
    𝗠
    3.16
    𝗧
    3.06
    ر
    2.97
    ᴄ
    2.85
    ്രി
    2.72
    𝗝
    2.70
    ᴘ
    2.67
     frustration
    2.66
    Activations Density 0.065%

    No Known Activations