© 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. 10595
    Prev
    Next
    INDEX
    Explanations

    financial, historical, legal, or criminal contexts

    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
    Alors
    1.30
    ⺆
    1.20
     भजन
    1.20
     তারপরে
    1.18
    \$
    1.18
    ных
    1.17
    \#
    1.17
    </td>
    1.16
    పై
    1.15
    কারীর
    1.13
    POSITIVE LOGITS
    𝙩
    1.52
    𝙎
    1.48
    𝙝
    1.32
    imeters
    1.32
     sorts
    1.25
    𝙮
    1.23
    𝘽
    1.23
    تان
    1.23
    ≳
    1.22
    𝙖
    1.21
    Activations Density 0.000%

    No Known Activations