© 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. 34-GEMMASCOPE-RES-131K
    7. 66216
    Prev
    Next
    INDEX
    Explanations

    names and words starting with man

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

    The neuron fires on substrings like “manu” or “mano” (e.g. in names such as Manu, Manoj, Manolo, Manus) – in other words, it detects that character sequence in tokens.

    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
    档案
    -0.74
    管道
    -0.73
    ombang
    -0.71
    kusen
    -0.69
     épouse
    -0.68
     scalability
    -0.68
    IRUS
    -0.68
     Стан
    -0.68
    Fung
    -0.68
    Stag
    -0.68
    POSITIVE LOGITS
    cheri
    0.85
     बजाय
    0.77
    many
    0.77
    millions
    0.73
    cher
    0.73
    pendientes
    0.73
    borrar
    0.73
    takes
    0.72
    charged
    0.71
    considered
    0.71
    Activations Density 0.041%

    No Known Activations