© 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. 59093
    Prev
    Next
    INDEX
    Explanations

    scale and loops

    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
     getTarget
    -0.85
    Attacks
    -0.81
    Playa
    -0.80
    hatsu
    -0.76
    Pinus
    -0.75
    tmpdir
    -0.75
    采用
    -0.74
     lópez
    -0.73
    eynman
    -0.73
     thấm
    -0.73
    POSITIVE LOGITS
    Ŗ
    0.81
     privé
    0.79
     ohms
    0.79
    stā
    0.79
    baar
    0.76
    bü
    0.75
    offer
    0.75
    onto
    0.74
    anglement
    0.73
    旋律
    0.72
    Activations Density 0.005%

    No Known Activations