© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31742
    Prev
    Next
    INDEX
    Explanations

    names of Acts

    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
     like
    -1.19
     such
    -1.11
     associated
    -1.09
     including
    -1.08
     about
    -1.06
     approximately
    -1.05
     advised
    -1.03
    hodné
    -1.03
    際に
    -1.00
     determined
    -1.00
    POSITIVE LOGITS
     remé
    1.15
     תש
    1.08
     favoriser
    1.05
    kening
    1.04
     rembourse
    1.01
     inond
    1.00
    Act
    0.96
     plafon
    0.96
     réve
    0.95
     profesora
    0.95
    Activations Density 0.028%

    No Known Activations