© 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. 4161
    Prev
    Next
    INDEX
    Explanations

    Sh, S, Tash, Mash, Shay

    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
    marginRight
    -0.94
    amping
    -0.83
    込め
    -0.82
    iph
    -0.81
     retard
    -0.80
     Golfo
    -0.78
    noční
    -0.77
    む
    -0.77
     отка
    -0.76
     INNOV
    -0.76
    POSITIVE LOGITS
     ziemlich
    0.81
    Estudios
    0.74
     trinken
    0.73
     work
    0.73
     felt
    0.71
     included
    0.71
    conhe
    0.70
    #
    0.70
    Moth
    0.69
     practically
    0.69
    Activations Density 0.008%

    No Known Activations