© 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. 22-GEMMASCOPE-RES-131K
    7. 16042
    Prev
    Next
    INDEX
    Explanations

    `value` and `short` in code

    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_22/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
     Hauteur
    -1.13
     Commencez
    -1.05
    fordshire
    -1.05
     poupée
    -1.02
    grip
    -1.01
     Karena
    -0.97
    maksi
    -0.97
     OBITUARY
    -0.96
     fiducia
    -0.96
    ◮
    -0.95
    POSITIVE LOGITS
    ということです
    1.20
    section
    1.11
     instead
    1.02
    ckte
    0.99
    path
    0.99
    𝟏
    0.98
    ということ
    0.98
    onekana
    0.97
    һ
    0.96
     hallowed
    0.96
    Activations Density 0.000%

    No Known Activations