© 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. 10-GEMMASCOPE-RES-131K
    4. 3845
    Prev
    Next
    INDEX
    Explanations

    private key marker

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

    The neuron flags characters typical of Base64‐encoded data (e.g. “/”, uppercase and lowercase letters like P, Q, g, r) indicating embedded encoded key or blob.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    These
    -1.66
    contoh
    -1.44
    produktion
    -1.33
    اااا
    -1.30
     этой
    -1.30
     téléchargement
    -1.25
     لهذه
    -1.24
     مشابه
    -1.23
    Both
    -1.23
     इन
    -1.23
    POSITIVE LOGITS
     such
    2.06
     to
    1.56
     then
    1.55
     Then
    1.52
    𖥧
    1.52
     музыки
    1.49
     に関する
    1.49
    vyšší
    1.42
     któ
    1.41
     있다
    1.41
    Activations Density 0.001%

    No Known Activations