© 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. 2315
    Prev
    Next
    INDEX
    Explanations

    llama.cpp usage locally

    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
    াপন্ন
    1.62
    ৭
    1.59
    <0x80>
    1.56
    likle
    1.55
    ε
    1.53
     ellipso
    1.53
     mieux
    1.53
    sburg
    1.51
    ся
    1.49
     achet
    1.48
    POSITIVE LOGITS
     ordinance
    1.87
    ့
    1.76
    ȱ
    1.75
     ऐसा
    1.73
    otherapy
    1.73
    \-
    1.70
    Pentru
    1.66
     साथ
    1.65
     darah
    1.64
    न्हें
    1.63
    Activations Density 0.183%

    No Known Activations