© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10776
    Prev
    Next
    INDEX
    Explanations

    escaping or leaving

    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_22_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
    chter
    1.07
     suspect
    0.97
    னு
    0.97
    대
    0.95
    ख
    0.94
     outsiders
    0.94
    queda
    0.94
    અ
    0.94
    بد
    0.94
     Lebesgue
    0.93
    POSITIVE LOGITS
     khỏi
    1.42
     daqui
    0.96
    ಂಡ
    0.94
    ENCES
    0.93
     heißt
    0.93
     دادن
    0.91
    adus
    0.91
     therefrom
    0.91
     mái
    0.90
    wires
    0.88
    Activations Density 0.054%

    No Known Activations