© 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. 1437
    Prev
    Next
    INDEX
    Explanations

    html structure

    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
    <0x80>
    1.85
    l
    1.79
    ik
    1.58
    synth
    1.54
    nof
    1.52
    habitude
    1.48
    lone
    1.47
    น้ำ
    1.46
    น
    1.46
    䛺
    1.42
    POSITIVE LOGITS
     defects
    1.58
     буквально
    1.55
    Corollary
    1.53
    اتف
    1.53
     Simplified
    1.52
    venor
    1.50
     conjugated
    1.49
    Collins
    1.49
     assesses
    1.49
     Católica
    1.47
    Activations Density 0.060%

    No Known Activations