© 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. 1599
    Prev
    Next
    INDEX
    Explanations

    threat, rare, bleak, relatively

    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
    larda
    3.37
    pped
    3.26
    ש
    3.09
    ार
    3.07
    一个
    2.97
    ార్
    2.93
    ے
    2.91
    istic
    2.91
    ان
    2.87
    た
    2.85
    POSITIVE LOGITS
    ्स
    5.50
    ی
    4.34
     זאת
    3.50
    nh
    3.16
    י
    3.13
    ند
    3.01
    i
    2.96
    nce
    2.89
    ้
    2.86
    leys
    2.80
    Activations Density 1.083%

    No Known Activations