© 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. 78520
    Prev
    Next
    INDEX
    Explanations

    technical computing and data concepts

    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
    contained
    -1.20
    concer
    -1.15
    га
    -1.10
    regarding
    -1.02
    Concerning
    -1.02
    ankind
    -1.02
     "/")
    -1.02
     fantastic
    -1.01
     ect
    -1.00
     lessened
    -1.00
    POSITIVE LOGITS
     upto
    1.89
     atleast
    1.77
     equipments
    1.36
     till
    1.34
     artistes
    1.31
    upto
    1.29
     alphabets
    1.28
     erst
    1.27
     learnt
    1.27
    noOf
    1.24
    Activations Density 0.314%

    No Known Activations