© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109749
    Prev
    Next
    INDEX
    Explanations

    Public keys or license rights

    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_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
    Jeff
    -0.78
     collaborazione
    -0.71
     compagni
    -0.69
    Ἥ
    -0.68
     suprême
    -0.67
    ⋆
    -0.65
    dler
    -0.64
    >?
    -0.63
    ریف
    -0.63
    ZONE
    -0.62
    POSITIVE LOGITS
     incred
    0.69
    СТВА
    0.69
     Bian
    0.68
     файла
    0.67
     petrol
    0.66
     supervisor
    0.66
     fall
    0.65
    的数据
    0.65
     bit
    0.64
     Fall
    0.64
    Activations Density 0.065%

    No Known Activations