© 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. 1099
    Prev
    Next
    INDEX
    Explanations

    I am / you are followed by description

    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
    ه
    2.78
    ğı
    2.28
    𝘁
    2.24
     cler
    2.20
    י
    2.20
     Gelegenheit
    2.12
    heartedly
    2.12
    𝗴
    2.08
    𝓽
    2.07
    ein
    2.04
    POSITIVE LOGITS
    ка
    2.54
    на
    2.49
    at
    2.37
    ки
    2.32
    ical
    2.31
    j
    2.19
    ق
    2.15
    야
    1.95
    кат
    1.95
    ките
    1.94
    Activations Density 0.465%

    No Known Activations