© 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. 87218
    Prev
    Next
    INDEX
    Explanations

    numbers followed by names/dates

    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
    CMV
    -0.82
    could
    -0.81
    otella
    -0.76
    lapsible
    -0.75
    vatore
    -0.73
    Chrys
    -0.73
    esterol
    -0.73
    ковский
    -0.73
    rigkeit
    -0.72
    ńskiego
    -0.71
    POSITIVE LOGITS
     YC
    1.47
    vc
    1.43
     MC
    1.42
     JC
    1.41
    MC
    1.40
    wc
    1.38
     WC
    1.38
    YC
    1.36
     FC
    1.35
    linec
    1.35
    Activations Density 0.093%

    No Known Activations