© 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. 34-GEMMASCOPE-RES-131K
    4. 98031
    Prev
    Next
    INDEX
    Explanations

    names starting with Alf or Alph

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

    The neuron strongly activates on character sequences like “alf” or “alph” (e.g. in names or brand terms such as Alphason, Alfassi, Alfentanil, Alfalfa, etc.).

    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
     لو
    -0.75
    plaatst
    -0.72
    вно
    -0.70
    mAuth
    -0.69
     aprire
    -0.69
     УК
    -0.68
     uint
    -0.65
     کافی
    -0.65
     경
    -0.63
    Pop
    -0.63
    POSITIVE LOGITS
    κίνη
    0.82
    beto
    0.82
    iate
    0.82
     Alfa
    0.81
    REQU
    0.77
    разу
    0.77
     ⇒
    0.73
     Romeo
    0.73
     alf
    0.73
     Alf
    0.72
    Activations Density 0.020%

    No Known Activations