© 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. 107365
    Prev
    Next
    INDEX
    Explanations

    meta-analysis

    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
     Gam
    -0.81
    Chassis
    -0.76
     Ris
    -0.76
     Spar
    -0.76
     Ato
    -0.75
     -=
    -0.75
     Assay
    -0.74
     Madison
    -0.74
    циали
    -0.73
    cased
    -0.73
    POSITIVE LOGITS
     meta
    5.06
    meta
    3.83
    Meta
    3.55
     Meta
    3.42
     мета
    3.16
    META
    3.03
     méta
    2.97
     META
    2.88
    メタ
    2.36
     metas
    2.30
    Activations Density 0.280%

    No Known Activations