© 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-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 502
    Prev
    Next
    INDEX
    Explanations

    initial numbers and ordinals

    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
     in
    -1.16
     recently
    -1.13
     but
    -1.01
    recently
    -0.92
     of
    -0.91
     seguimos
    -0.91
    ではまた
    -0.91
    鏡頭
    -0.91
     pensamos
    -0.87
    Recently
    -0.85
    POSITIVE LOGITS
     initial
    1.35
     earliest
    1.14
     initially
    1.12
    초
    1.09
    最初
    1.07
     primeras
    1.05
    initial
    1.04
     Initial
    1.02
     initiale
    1.01
    แรก
    0.99
    Activations Density 0.036%

    No Known Activations