© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 135152
    Prev
    Next
    INDEX
    Explanations

    soft and flexible materials

    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_40_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
     conservative
    0.52
     conservatives
    0.49
    Conservative
    0.47
    限制
    0.47
     conservatively
    0.47
    㝒
    0.47
    固
    0.47
     restrictive
    0.46
    顽
    0.46
    坚
    0.45
    POSITIVE LOGITS
     soft
    1.40
     softness
    1.34
     softer
    1.32
     Soft
    1.27
    柔らか
    1.27
     мяг
    1.25
    Soft
    1.23
    软
    1.23
    soft
    1.21
     SOFT
    1.21
    Activations Density 0.160%

    No Known Activations