© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 2624
    Prev
    Next
    INDEX
    Explanations

    describes states or conditions

    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
    1.68
    O
    1.62
    ه
    1.40
    ap
    1.39
    o
    1.38
    𝗸
    1.32
    I
    1.32
    場
    1.32
    ａ
    1.31
    ices
    1.29
    POSITIVE LOGITS
    ními
    1.39
     następnie
    1.35
     ďal
    1.33
     volna
    1.29
     دى
    1.29
     armazen
    1.28
    浈
    1.28
    这次
    1.27
     abras
    1.27
     tanggal
    1.27
    Activations Density 0.336%

    No Known Activations