© 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. 22-GEMMASCOPE-2-RES-16K
    7. 2870
    Prev
    Next
    INDEX
    Explanations

    abbreviations and their expansions

    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
    е
    1.08
    г
    0.95
    й
    0.91
    ścia
    0.88
    п
    0.86
    та
    0.84
    ہ
    0.83
     tap
    0.82
    м
    0.81
     s
    0.80
    POSITIVE LOGITS
    IL
    1.15
    dato
    1.12
     któ
    1.12
     sostanz
    1.11
    IVAL
    1.10
    ETIME
    1.08
    ERS
    1.08
    cado
    1.07
     Versorgung
    1.05
    ™
    1.05
    Activations Density 0.487%

    No Known Activations