© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 25898
    Prev
    Next
    INDEX
    Explanations

    composition 'of'

    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
     our
    -1.26
     all
    -1.15
     and
    -1.13
     every
    -1.07
     as
    -1.03
     verá
    -1.02
    に到着
    -0.97
     through
    -0.96
    会う
    -0.92
     or
    -0.91
    POSITIVE LOGITS
     généralement
    1.30
    usually
    1.22
    Either
    1.20
    often
    1.11
    Highly
    1.09
     souvent
    1.05
     mme
    1.05
    روش
    1.04
     douane
    1.04
    ATHY
    1.03
    Activations Density 0.648%

    No Known Activations