© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 310
    Prev
    Next
    INDEX
    Explanations

    numbers preceding quantities or identifiers

    np_acts-logits-general · gemini-2.5-flash-lite

    numbers and ratings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     groupBox
    0.28
     appBar
    0.24
     작업을
    0.23
     indiquer
    0.23
    𒁾
    0.22
     attribut
    0.22
     paysans
    0.22
     initialise
    0.22
     unlink
    0.21
    getBlueTeam
    0.21
    POSITIVE LOGITS
    0.35
    0
    0.34
    2
    0.30
    1
    0.29
    4
    0.28
    ii
    0.26
    3
    0.25
    5
    0.25
    www
    0.23
    or
    0.23
    Activations Density 0.647%

    No Known Activations