© 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
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-16K
    4. 2172
    Prev
    Next
    INDEX
    Explanations

    <start_of_turn>

    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
     fledgling
    0.98
     dwindling
    0.90
     aforementioned
    0.89
     mischievous
    0.86
    spirational
    0.86
     heterogeneous
    0.86
     fluctuating
    0.85
    ㇂
    0.85
    𝗍
    0.85
     confining
    0.84
    POSITIVE LOGITS
    e
    1.69
    er
    1.58
    en
    1.54
    ه
    1.51
    ে
    1.30
    o
    1.28
    ו
    1.24
    u
    1.23
    ة
    1.21
    ن
    1.20
    Activations Density 0.455%

    No Known Activations