© 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. 26263
    Prev
    Next
    INDEX
    Explanations

    getting prizes and rewards

    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
     большинстве
    -1.10
     or
    -1.03
    férés
    -0.99
    complished
    -0.98
    unción
    -0.98
    fordable
    -0.95
     exclusivamente
    -0.92
     MAKING
    -0.91
    τικών
    -0.90
     този
    -0.89
    POSITIVE LOGITS
     reward
    1.33
     rewarded
    1.30
     rewards
    1.19
     a
    1.01
    至少
    1.00
     récompense
    0.99
     được
    0.98
    lagte
    0.97
     TreeNode
    0.96
     various
    0.95
    Activations Density 0.031%

    No Known Activations