© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 38915
    Prev
    Next
    INDEX
    Explanations

    velocity and impact

    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_262k_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
    标准化
    0.53
    Tourism
    0.49
    坳
    0.46
     уні
    0.46
    袅
    0.46
    珼
    0.45
    谛
    0.44
    ู้
    0.44
    tourism
    0.44
     Tourism
    0.43
    POSITIVE LOGITS
     velocity
    0.92
     velocities
    0.88
     Velocity
    0.75
    velocity
    0.74
     recoil
    0.70
     collision
    0.69
     momentum
    0.69
     velocidade
    0.67
    Velocity
    0.66
     shock
    0.66
    Activations Density 0.063%

    No Known Activations