© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116181
    Prev
    Next
    INDEX
    Explanations

    induction processes and assumptions

    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
     Espírito
    -0.91
     benih
    -0.84
    _|
    -0.84
     dirs
    -0.77
     KAM
    -0.75
     olymp
    -0.75
    butter
    -0.74
     Strut
    -0.74
     Batal
    -0.73
     WrestleMania
    -0.73
    POSITIVE LOGITS
     Singular
    0.77
     Play
    0.77
     Witnesses
    0.76
     Particles
    0.76
     censored
    0.73
     Rechte
    0.73
     hornblende
    0.73
    备份
    0.69
    こだわ
    0.68
    Rob
    0.68
    Activations Density 0.035%

    No Known Activations