© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 17278
    Prev
    Next
    INDEX
    Explanations

    parts of regions

    np_acts-logits-general · gemini-2.5-flash-lite

    regions and their parts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    component
    0.50
    components
    0.45
    OS
    0.45
    焦点
    0.44
    w
    0.44
     Findings
    0.43
    接着
    0.42
     টাকা
    0.42
     时
    0.42
    ires
    0.42
    POSITIVE LOGITS
     Christendom
    0.55
     erreichen
    0.44
     Europe
    0.43
     throughout
    0.43
     całej
    0.42
     cann
    0.42
     decimated
    0.42
     ئەم
    0.41
     this
    0.41
     ogr
    0.41
    Activations Density 0.041%

    No Known Activations