© 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. 38242
    Prev
    Next
    INDEX
    Explanations

    names containing land

    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
    νης
    -0.93
     mercados
    -0.91
    elemField
    -0.85
    impinan
    -0.79
     ओर
    -0.76
    Lies
    -0.75
    ⅽ
    -0.73
     uncertain
    -0.73
    candid
    -0.72
    ඞ
    -0.72
    POSITIVE LOGITS
    ers
    1.13
     theses
    0.90
    icity
    0.90
    rea
    0.89
    their
    0.87
    ish
    0.85
    sk
    0.85
    虽
    0.84
    REA
    0.84
     Incluso
    0.82
    Activations Density 0.025%

    No Known Activations