© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 6627
    Prev
    Next
    INDEX
    Explanations

    discount factor for rewards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     butternut
    0.45
     Amongst
    0.45
     Depending
    0.45
    鼈
    0.45
     caucus
    0.45
     देश
    0.43
     escritura
    0.43
     Our
    0.43
     Your
    0.43
     kettle
    0.43
    POSITIVE LOGITS
    }",
    0.52
    ytics
    0.48
    نين
    0.48
    },
    0.47
    pt
    0.46
    <0x94>
    0.45
    limit
    0.45
    ut
    0.44
    ru
    0.43
     beschäftigt
    0.43
    Activations Density 0.005%

    No Known Activations