© 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. 710
    Prev
    Next
    INDEX
    Explanations

    apache, LOAD DATA, Q:

    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
    stim
    -0.72
    онов
    -0.72
    세
    -0.71
    クレ
    -0.70
     Don
    -0.69
    sätzlich
    -0.69
     crescere
    -0.68
    ὶ
    -0.68
     آر
    -0.67
    无声
    -0.67
    POSITIVE LOGITS
     OIL
    0.82
    鼹
    0.81
    oznam
    0.78
     zb
    0.76
     forder
    0.75
     aviones
    0.75
    HTC
    0.74
     autén
    0.73
    rouw
    0.73
     auténtico
    0.73
    Activations Density 0.014%

    No Known Activations