© 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. 1605
    Prev
    Next
    INDEX
    Explanations

    description / question

    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
    த்
    1.51
    𝐬
    1.49
     outliers
    1.48
    <unused1110>
    1.47
    விட்டு
    1.44
     abnormalities
    1.44
     macrophages
    1.44
     worsened
    1.44
    <unused187>
    1.44
    <unused194>
    1.44
    POSITIVE LOGITS
    a
    1.61
     possui
    1.42
    <0x80>
    1.40
    sa
    1.37
     Accessed
    1.34
    zyna
    1.34
    é
    1.23
    ర్జ
    1.22
    േക്ക്
    1.20
     tengas
    1.20
    Activations Density 0.504%

    No Known Activations