© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6934
    Prev
    Next
    INDEX
    Explanations

    reinforcement learning and 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_16k_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
    汶
    0.46
     музе
    0.46
    mxCell
    0.45
    分页
    0.44
    ፈል
    0.43
    RIBUTE
    0.42
    fonts
    0.42
    owels
    0.42
    빅
    0.42
    粼
    0.42
    POSITIVE LOGITS
     rewards
    0.68
     reward
    0.66
    報酬
    0.66
     gameplay
    0.65
     belajar
    0.61
     Rewards
    0.60
     learns
    0.60
     Gameplay
    0.58
     behavioral
    0.57
     rewarded
    0.57
    Activations Density 0.244%

    No Known Activations