© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117069
    Prev
    Next
    INDEX
    Explanations

    numbers followed by numbers

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

    It detects numeric digit tokens (i.e. standalone numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    articolo
    -1.14
    ت
    -1.06
    骓
    -1.04
    中心的
    -1.02
    readFileSync
    -1.02
     entreprise
    -1.02
     stupid
    -1.01
    鐃
    -1.01
    に行きました
    -1.00
    ஂ
    -0.97
    POSITIVE LOGITS
    ఱ
    1.15
    th
    1.10
     compet
    1.10
    进制
    1.05
    apor
    1.02
     Franse
    1.01
    OZ
    1.00
    um
    1.00
     kullanılır
    1.00
     клапа
    1.00
    Activations Density 0.056%

    No Known Activations