© 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
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-16K
    4. 10707
    Prev
    Next
    INDEX
    Explanations

    programming language data types and structures

    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
     ruining
    0.85
     इंपोर्टेंट
    0.79
    )</
    0.78
     illustrating
    0.75
     $=
    0.75
     wires
    0.74
     ſh
    0.73
     unterwegs
    0.73
     drawers
    0.72
     ):
    0.72
    POSITIVE LOGITS
    []
    3.07
    [][]
    2.40
     []
    2.39
    []=
    2.31
    [][
    2.19
    [],
    2.18
    [];
    2.15
    [])
    2.00
    []{
    1.95
     [][]
    1.92
    Activations Density 0.043%

    No Known Activations