© 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. 110683
    Prev
    Next
    INDEX
    Explanations

    Mata names

    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
     marav
    -0.87
     voort
    -0.82
    ynia
    -0.78
     }^{*}
    -0.78
    バレ
    -0.77
    ੋਂ
    -0.76
     м
    -0.72
     adorable
    -0.72
     США
    -0.72
     brz
    -0.71
    POSITIVE LOGITS
     anhand
    0.85
     locais
    0.77
    ♞
    0.75
     ——
    0.73
    ્ય
    0.73
    DAM
    0.71
     …”
    0.71
    ུ་
    0.70
     Fremantle
    0.69
    спек
    0.69
    Activations Density 0.016%

    No Known Activations