© 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. 23667
    Prev
    Next
    INDEX
    Explanations

    XML and code attributes

    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
     Faust
    -0.78
     sym
    -0.76
     clasp
    -0.75
     Hyd
    -0.74
    fillStyle
    -0.74
     Tau
    -0.73
    uster
    -0.73
     Aust
    -0.71
     Reno
    -0.71
     Mann
    -0.69
    POSITIVE LOGITS
    hamster
    0.79
     PRIME
    0.79
     Orto
    0.74
    unse
    0.72
     слабо
    0.72
    ranje
    0.71
    哮
    0.71
     râ
    0.71
     休
    0.70
     kleineren
    0.70
    Activations Density 0.051%

    No Known Activations