© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 63162
    Prev
    Next
    INDEX
    Explanations

    see it or ourselves

    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
    曲目
    -1.02
    ARDI
    -0.95
    EFFECT
    -0.94
    whether
    -0.91
    沵
    -0.91
    çando
    -0.90
     ambienti
    -0.90
     是否
    -0.89
    argout
    -0.88
     þe
    -0.87
    POSITIVE LOGITS
     value
    1.58
     opportunities
    1.52
     opportunity
    1.50
     possibilities
    1.43
     parallels
    1.39
     through
    1.36
     potential
    1.35
    value
    1.32
     mulighed
    1.24
     possibilità
    1.23
    Activations Density 0.019%

    No Known Activations