© 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. 1677
    Prev
    Next
    INDEX
    Explanations

    programming language keywords `let`

    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
    e
    1.36
    eer
    1.20
    ে
    1.16
    ever
    1.12
     minim
    1.10
    een
    1.10
    ibid
    1.09
    s
    1.06
     '
    1.05
    y
    1.03
    POSITIVE LOGITS
     whopping
    1.72
     û
    1.68
    𝚔
    1.61
     dilapidated
    1.59
    वहीं
    1.58
    ﺘ
    1.58
    𝚒
    1.58
    robespierre
    1.57
     foothold
    1.57
     foray
    1.53
    Activations Density 0.004%

    No Known Activations