© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 67305
    Prev
    Next
    INDEX
    Explanations

    keys or identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    และ
    -1.52
     และ
    -1.43
    opie
    -1.23
    巂
    -1.20
     ส่วน
    -1.20
    尨
    -1.19
    
    -1.18
    姽
    -1.17
    thas
    -1.16
    媗
    -1.16
    POSITIVE LOGITS
     when
    1.36
     as
    1.34
     amidst
    1.21
     after
    1.20
    —
    1.20
     of
    1.13
     although
    1.13
     in
    1.10
     playful
    1.10
     at
    1.09
    Activations Density 0.012%

    No Known Activations