© 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. 81219
    Prev
    Next
    INDEX
    Explanations

    fictional character comparisons

    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
    อาด
    -0.79
     utvik
    -0.79
     skjø
    -0.78
    pya
    -0.77
    conditional
    -0.76
     program
    -0.75
    瑩
    -0.74
     megold
    -0.71
     anledning
    -0.71
    tech
    -0.71
    POSITIVE LOGITS
     feats
    1.02
     compi
    0.85
    Mismatch
    0.84
     peniten
    0.84
     CBR
    0.83
     Kurse
    0.81
     漫
    0.81
    @_
    0.81
    @
    0.79
    ์ตูน
    0.78
    Activations Density 0.002%

    No Known Activations